crates/hub/src/config.rs at 33d98147511b · andymccall/oxygenhub

# 33d98147511b oxygenhub / crates / hub / src / config.rs
21.6 KiB · Rust · last changed Run the hub as web and worker processes, singletons under a leader lock 17 days ago source blame history raw
//! Configuration (hub spec §17.1): `hub.toml` in the data directory, every
//! key overridable by `OXYHUB_<SECTION>_<KEY>`.

use serde::Deserialize;
use std::net::SocketAddr;
use std::path::{Path, PathBuf};

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Config {
    /// Set from the command line, never from the file.
    #[serde(skip)]
    pub data: PathBuf,
    pub site: Site,
    pub server: Server,
    pub tls: Tls,
    pub auth: Auth,
    pub registration: Registration,
    pub email: Email,
    pub limits: Limits,
    pub retention: Retention,
    pub flow: Flow,
    pub apt: Apt,
    pub diffusion: Diffusion,
    pub backups: Backups,
    pub outbound: Outbound,
    pub database: Database,
    pub tlog: Tlog,
}

/// Where a hub built with the `postgres` feature keeps its tables (#211); a
/// SQLite build keeps them in `<data>/hub.db` and ignores this.
#[derive(Clone, Debug, Default, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Database {
    /// `postgres://user@host/db`; the password from the URL or `PGPASSWORD`.
    pub url: String,
    /// The schema to use, made if missing; empty for `public`, `*` for one
    /// per data directory (named after it), as the tests use.
    pub schema: String,
}

/// Outbound requests to addresses people give (oxygenhub#219): private
/// and local addresses are refused unless listed here, as `scheme://host`
/// (any port) or `scheme://host:port`, e.g. a local Ollama:
/// `allow = ["http://127.0.0.1:11434"]`.
#[derive(Clone, Debug, Default, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Outbound {
    pub allow: Vec<String>,
}

/// The transparency log's witnesses (docs/transparency.md, #238): who
/// cosigns this hub's checkpoints, and whose logs this hub cosigns.
#[derive(Clone, Debug, Default, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Tlog {
    pub witnesses: Vec<TlogWitness>,
    pub witness_for: Vec<TlogWitnessed>,
}

/// A witness this hub's log asks: its name in cosignatures, its
/// add-checkpoint address (`https://HUB/log/witness/add-checkpoint` for
/// another hub), and its identity object in base64 (another hub's
/// `/.well-known/oxyhub-key`).
#[derive(Clone, Debug, Deserialize)]
#[serde(deny_unknown_fields)]
pub struct TlogWitness {
    pub name: String,
    pub url: String,
    pub key: String,
}

/// A log this hub witnesses: its origin (`HOST/log`) and its key, an
/// identity object in base64.
#[derive(Clone, Debug, Deserialize)]
#[serde(deny_unknown_fields)]
pub struct TlogWitnessed {
    pub origin: String,
    pub key: String,
}

/// Backups (docs/backups.md, oxygenhub#169): the directories on this host
/// an owner may back up to. Empty, only GCS destinations can be chosen.
#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Backups {
    pub directories: Vec<PathBuf>,
    /// Google's token exchange and Cloud Storage, for GCS destinations;
    /// set only to point them elsewhere (tests, a private endpoint).
    pub sts_url: String,
    pub storage_url: String,
    /// AWS STS and S3, for S3 destinations; `{bucket}` and `{region}` in
    /// `s3_url` are filled in. Set only to point them elsewhere.
    pub aws_sts_url: String,
    pub s3_url: String,
}

impl Default for Backups {
    fn default() -> Self {
        Backups {
            directories: Vec::new(),
            sts_url: "https://sts.googleapis.com".into(),
            storage_url: "https://storage.googleapis.com".into(),
            aws_sts_url: "https://sts.amazonaws.com".into(),
            s3_url: "https://{bucket}.s3.{region}.amazonaws.com".into(),
        }
    }
}

/// Diffusion (#148, docs/diffusion.md §4.2): the site's default for
/// repositories that say nothing.
#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Diffusion {
    /// `off`, `green` or `any`.
    pub follow: String,
}

impl Default for Diffusion {
    fn default() -> Self {
        Diffusion { follow: "off".into() }
    }
}

/// The apt repository at `/apt` (oxygenhub#85): the `.deb` assets of these
/// public repositories' releases, signed with the key in `gnupg_home`.
#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Apt {
    /// `owner/name` of each repository whose release `.deb`s are served;
    /// none turns `/apt` off.
    pub repos: Vec<String>,
    /// The suite apt's `sources` names.
    pub suite: String,
    pub component: String,
    /// GnuPG home holding the signing key (relative to the data directory).
    pub gnupg_home: String,
    /// Architectures the index lists, each with its Packages file.
    pub architectures: Vec<String>,
}

impl Default for Apt {
    fn default() -> Self {
        Apt {
            repos: vec![],
            suite: "stable".into(),
            component: "main".into(),
            gnupg_home: "apt-gnupg".into(),
            architectures: vec!["amd64".into(), "arm64".into(), "riscv64".into()],
        }
    }
}

/// OxygenFlow runs (hub spec §13.2).
#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Flow {
    /// Bearer tokens runners present to claim jobs.
    pub runner_tokens: Vec<String>,
    /// `owner/*` or `owner/name`: repositories whose pushes start runs.
    pub repos: Vec<String>,
    pub job_timeout_minutes: u64,
    /// A runner whose last this many jobs all ended in an infrastructure
    /// error (status `error`, not `failed`) is drained and the
    /// administrators told (oxygenflow#30); 0 never drains one.
    pub drain_after_errors: u32,
}

impl Default for Flow {
    fn default() -> Self {
        Flow { runner_tokens: vec![], repos: vec![], job_timeout_minutes: 60, drain_after_errors: 5 }
    }
}

impl Flow {
    /// Whether pushes to `owner/name` start runs.
    pub fn allows(&self, owner: &str, name: &str) -> bool {
        self.repos.iter().any(|p| match p.split_once('/') {
            Some((o, "*")) => o == owner,
            Some((o, n)) => o == owner && n == name,
            None => false,
        })
    }
}

#[derive(Clone, Debug, Default, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Email {
    /// `smtp://user:pass@host:port` or `smtps://…`; empty disables email.
    pub smtp: String,
    /// `OxygenHub <hub@example>`.
    pub from: String,
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Registration {
    /// `open`, `invite` or `closed`; the admin page can override it.
    pub mode: String,
    /// The setup code the first account must bring (oxygenhub#245), for
    /// automation; empty, the hub makes one and keeps it in
    /// `<data>/setup-code`.
    pub setup_code: String,
}

impl Default for Registration {
    fn default() -> Self {
        Registration { mode: "invite".into(), setup_code: String::new() }
    }
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Site {
    pub name: String,
    pub description: String,
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Server {
    /// Plain HTTP; empty disables it.
    pub bind: String,
    /// HTTPS; empty disables it. Needs `tls`.
    pub tls_bind: String,
    /// What links and clone URLs start with.
    pub base_url: String,
    /// Trust `X-Forwarded-*` from a terminating proxy.
    pub behind_proxy: bool,
    /// Strict-Transport-Security's max-age in seconds, sent when
    /// `base_url` is https; 0 sends none (oxygenhub#231). Raise it in
    /// stages: browsers keep it, so it is hard to take back.
    pub hsts_max_age: u64,
    /// The bearer token `/metrics` asks for (oxygenhub#212); empty, the
    /// metrics are off.
    pub metrics_token: String,
    /// A Grafana for this hub's metrics, linked from Insights (oxygenhub#257)
    /// for charts of one's own; empty, no link.
    pub grafana_url: String,
    /// What this process does (docs/roles.md, #272): `web` (pages, the
    /// API, the wire protocol, the runner API) and `worker` (the background
    /// tasks). Empty, both. `serve --role` overrides it.
    pub roles: Vec<String>,
}

/// One part of the hub's work a process can take (docs/roles.md, #272).
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum Role {
    /// Pages, the JSON API, the wire protocol, live pages and the runner
    /// API, and the transparency log they append to.
    Web,
    /// The background tasks: webhooks, Flow's scheduler, reaper and
    /// placement pass, nightly upkeep, backups and Diffusion's index.
    Worker,
}

impl Role {
    pub const ALL: [Role; 2] = [Role::Web, Role::Worker];

    pub fn name(self) -> &'static str {
        match self {
            Role::Web => "web",
            Role::Worker => "worker",
        }
    }
}

impl std::str::FromStr for Role {
    type Err = String;

    fn from_str(s: &str) -> Result<Role, String> {
        match s.trim().to_ascii_lowercase().as_str() {
            "web" => Ok(Role::Web),
            "worker" => Ok(Role::Worker),
            _ => Err(format!("unknown role {:?}: the roles are web and worker", s.trim())),
        }
    }
}

/// The roles one process takes: every role unless some are named.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct Roles {
    pub web: bool,
    pub worker: bool,
}

impl Default for Roles {
    fn default() -> Self {
        Roles { web: true, worker: true }
    }
}

impl Roles {
    /// The roles named, each `web` or `worker`; none named is every role.
    pub fn from_names<S: AsRef<str>>(names: &[S]) -> Result<Roles, String> {
        let names: Vec<&str> = names.iter().map(|s| s.as_ref().trim()).filter(|s| !s.is_empty()).collect();
        if names.is_empty() {
            return Ok(Roles::default());
        }
        let mut roles = Roles { web: false, worker: false };
        for n in names {
            match n.parse::<Role>()? {
                Role::Web => roles.web = true,
                Role::Worker => roles.worker = true,
            }
        }
        Ok(roles)
    }

    pub fn has(self, role: Role) -> bool {
        match role {
            Role::Web => self.web,
            Role::Worker => self.worker,
        }
    }

    /// The roles' names, in a fixed order: what `/health` reports.
    pub fn names(self) -> Vec<&'static str> {
        Role::ALL.into_iter().filter(|r| self.has(*r)).map(Role::name).collect()
    }
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Tls {
    /// Generate a certificate at `init` (developer edition).
    pub self_signed: bool,
    /// PEM files; relative paths are under the data directory.
    pub cert: String,
    pub key: String,
}

#[derive(Clone, Debug, Default, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Auth {
    /// Bearer tokens allowed to push until accounts exist (hub 0.2). Empty
    /// means every push is accepted, as `oxy serve` does.
    pub push_tokens: Vec<String>,
    /// For tests only: a base URL that stands in for every sign-in
    /// provider (`{base}/{provider}/authorize|token|userinfo`).
    pub signin_mock: Option<String>,
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Limits {
    /// Largest file rendered in the browser, e.g. `2MiB`.
    pub render_limit: ByteSize,
    pub asset_limit: ByteSize,
    pub push_body_limit: ByteSize,
}

#[derive(Clone, Debug, Deserialize)]
#[serde(default, deny_unknown_fields)]
pub struct Retention {
    pub trash_days: u32,
    pub webhook_log_days: u32,
    /// The UTC hour at which every repository is garbage collected
    /// (spec §17.2); 24 or more turns the nightly gc off.
    pub gc_hour: u32,
}

/// A byte count written as `512`, `2MiB`, `4GiB`, `100kB`.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct ByteSize(pub u64);

impl ByteSize {
    pub fn parse(s: &str) -> Option<ByteSize> {
        let s = s.trim();
        let digits: String = s.chars().take_while(|c| c.is_ascii_digit()).collect();
        let unit = s[digits.len()..].trim();
        let n: u64 = digits.parse().ok()?;
        let mult = match unit {
            "" | "B" => 1,
            "k" | "kB" | "KB" => 1000,
            "KiB" | "K" => 1 << 10,
            "M" | "MB" => 1_000_000,
            "MiB" => 1 << 20,
            "G" | "GB" => 1_000_000_000,
            "GiB" => 1 << 30,
            _ => return None,
        };
        Some(ByteSize(n.checked_mul(mult)?))
    }
}

impl<'de> Deserialize<'de> for ByteSize {
    fn deserialize<D: serde::Deserializer<'de>>(d: D) -> Result<ByteSize, D::Error> {
        #[derive(Deserialize)]
        #[serde(untagged)]
        enum Raw {
            Number(u64),
            Text(String),
        }
        match Raw::deserialize(d)? {
            Raw::Number(n) => Ok(ByteSize(n)),
            Raw::Text(t) => ByteSize::parse(&t).ok_or_else(|| serde::de::Error::custom(format!("not a byte size: {t:?}"))),
        }
    }
}

impl Default for Site {
    fn default() -> Self {
        Site { name: "OxygenHub".into(), description: "Repositories, proposals and issues for Oxygen".into() }
    }
}

impl Default for Server {
    fn default() -> Self {
        Server {
            bind: "127.0.0.1:7300".into(),
            tls_bind: String::new(),
            base_url: "http://127.0.0.1:7300".into(),
            behind_proxy: false,
            hsts_max_age: 0,
            metrics_token: String::new(),
            grafana_url: String::new(),
            roles: Vec::new(),
        }
    }
}

impl Default for Tls {
    fn default() -> Self {
        Tls { self_signed: false, cert: "keys/tls.crt".into(), key: "keys/tls.key".into() }
    }
}

impl Default for Limits {
    fn default() -> Self {
        Limits { render_limit: ByteSize(2 << 20), asset_limit: ByteSize(512 << 20), push_body_limit: ByteSize(4 << 30) }
    }
}

impl Default for Retention {
    fn default() -> Self {
        Retention { trash_days: 30, webhook_log_days: 30, gc_hour: 3 }
    }
}

impl Default for Config {
    fn default() -> Self {
        Config {
            data: PathBuf::from("data"),
            site: Site::default(),
            server: Server::default(),
            tls: Tls::default(),
            auth: Auth::default(),
            registration: Registration::default(),
            email: Email::default(),
            limits: Limits::default(),
            retention: Retention::default(),
            flow: Flow::default(),
            apt: Apt::default(),
            diffusion: Diffusion::default(),
            backups: Backups::default(),
            outbound: Outbound::default(),
            database: Database::default(),
            tlog: Tlog::default(),
        }
    }
}

impl Config {
    /// Read `<data>/hub.toml` if present, then apply environment overrides.
    pub fn load(data: &Path) -> anyhow::Result<Config> {
        let path = data.join("hub.toml");
        let mut cfg = match std::fs::read_to_string(&path) {
            Ok(text) => Config::parse(&text)?,
            Err(e) if e.kind() == std::io::ErrorKind::NotFound => Config::default(),
            Err(e) => return Err(anyhow::anyhow!("reading {}: {e}", path.display())),
        };
        cfg.data = data.to_path_buf();
        cfg.apply_env(|k| std::env::var(k).ok());
        cfg.roles()?;
        Ok(cfg)
    }

    pub fn parse(text: &str) -> anyhow::Result<Config> {
        Ok(toml::from_str(text)?)
    }

    /// `OXYHUB_SERVER_BIND`, `OXYHUB_SITE_NAME`, … override the file.
    pub fn apply_env(&mut self, get: impl Fn(&str) -> Option<String>) {
        if let Some(v) = get("OXYHUB_DATABASE_URL") {
            self.database.url = v;
        }
        if let Some(v) = get("OXYHUB_DATABASE_SCHEMA") {
            self.database.schema = v;
        }
        if let Some(v) = get("OXYHUB_SITE_NAME") {
            self.site.name = v;
        }
        if let Some(v) = get("OXYHUB_SITE_DESCRIPTION") {
            self.site.description = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_BIND") {
            self.server.bind = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_TLS_BIND") {
            self.server.tls_bind = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_BASE_URL") {
            self.server.base_url = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_BEHIND_PROXY") {
            self.server.behind_proxy = matches!(v.as_str(), "1" | "true" | "yes");
        }
        if let Some(v) = get("OXYHUB_SERVER_HSTS_MAX_AGE") {
            self.server.hsts_max_age = v.parse().unwrap_or(0);
        }
        // The VM's setup gives these (oxygenhub-gcp#12): the token its
        // collector scrapes /metrics with, and its Grafana for Insights' link.
        if let Some(v) = get("OXYHUB_SERVER_METRICS_TOKEN") {
            self.server.metrics_token = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_GRAFANA_URL") {
            self.server.grafana_url = v;
        }
        if let Some(v) = get("OXYHUB_SERVER_ROLES") {
            self.server.roles = v.split(',').map(str::trim).filter(|s| !s.is_empty()).map(String::from).collect();
        }
        if let Some(v) = get("OXYHUB_TLS_SELF_SIGNED") {
            self.tls.self_signed = matches!(v.as_str(), "1" | "true" | "yes");
        }
        if let Some(v) = get("OXYHUB_REGISTRATION_MODE") {
            self.registration.mode = v;
        }
        if let Some(v) = get("OXYHUB_REGISTRATION_SETUP_CODE") {
            self.registration.setup_code = v;
        }
        if let Some(v) = get("OXYHUB_AUTH_PUSH_TOKENS") {
            self.auth.push_tokens = v.split(',').map(str::trim).filter(|s| !s.is_empty()).map(String::from).collect();
        }
        if let Some(v) = get("OXYHUB_LIMITS_RENDER_LIMIT").and_then(|v| ByteSize::parse(&v)) {
            self.limits.render_limit = v;
        }
    }

    /// This process's roles (`[server] roles`); an unknown name is an error.
    pub fn roles(&self) -> anyhow::Result<Roles> {
        Roles::from_names(&self.server.roles).map_err(|e| anyhow::anyhow!("[server] roles: {e}"))
    }

    pub fn bind_addr(&self) -> anyhow::Result<Option<SocketAddr>> {
        parse_addr(&self.server.bind)
    }

    pub fn tls_bind_addr(&self) -> anyhow::Result<Option<SocketAddr>> {
        parse_addr(&self.server.tls_bind)
    }

    pub fn tls_cert(&self) -> PathBuf {
        self.data.join(&self.tls.cert)
    }

    pub fn tls_key(&self) -> PathBuf {
        self.data.join(&self.tls.key)
    }

    pub fn repos_dir(&self) -> PathBuf {
        self.data.join("repos")
    }

    pub fn keys_dir(&self) -> PathBuf {
        self.data.join("keys")
    }

    pub fn db_path(&self) -> PathBuf {
        self.data.join("hub.db")
    }

    /// The base URL without a trailing slash.
    pub fn base_url(&self) -> &str {
        self.server.base_url.trim_end_matches('/')
    }
}

fn parse_addr(s: &str) -> anyhow::Result<Option<SocketAddr>> {
    if s.trim().is_empty() {
        return Ok(None);
    }
    Ok(Some(s.parse().map_err(|e| anyhow::anyhow!("bind address {s:?}: {e}"))?))
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn byte_sizes() {
        assert_eq!(ByteSize::parse("2MiB"), Some(ByteSize(2 << 20)));
        assert_eq!(ByteSize::parse("512"), Some(ByteSize(512)));
        assert_eq!(ByteSize::parse("4 GiB"), Some(ByteSize(4 << 30)));
        assert_eq!(ByteSize::parse("100kB"), Some(ByteSize(100_000)));
        assert_eq!(ByteSize::parse("lots"), None);
    }

    #[test]
    fn file_then_environment() {
        let mut cfg = Config::parse("[server]\nbind = \"0.0.0.0:7300\"\n[limits]\nrender_limit = \"1MiB\"\n").unwrap();
        assert_eq!(cfg.server.bind, "0.0.0.0:7300");
        assert_eq!(cfg.limits.render_limit, ByteSize(1 << 20));
        assert_eq!(cfg.site.name, "OxygenHub");
        cfg.apply_env(|k| match k {
            "OXYHUB_SITE_NAME" => Some("Earth".into()),
            "OXYHUB_AUTH_PUSH_TOKENS" => Some("a, b".into()),
            "OXYHUB_SERVER_METRICS_TOKEN" => Some("m".into()),
            "OXYHUB_SERVER_GRAFANA_URL" => Some("https://grafana.example".into()),
            _ => None,
        });
        assert_eq!(cfg.site.name, "Earth");
        assert_eq!(cfg.auth.push_tokens, ["a", "b"]);
        assert_eq!((cfg.server.metrics_token.as_str(), cfg.server.grafana_url.as_str()), ("m", "https://grafana.example"));
        assert!(Config::parse("[nope]\nx = 1\n").is_err(), "unknown sections are errors, not silence");
    }

    #[test]
    fn roles_default_to_all_and_unknown_names_are_errors() {
        let cfg = Config::default();
        assert_eq!(cfg.roles().unwrap(), Roles { web: true, worker: true });
        assert_eq!(cfg.roles().unwrap().names(), ["web", "worker"]);
        assert_eq!(Roles::from_names(&["worker"]).unwrap(), Roles { web: false, worker: true });
        assert_eq!(Roles::from_names(&[" Web ", "web"]).unwrap().names(), ["web"]);
        assert_eq!(Roles::from_names(&["worker", "web"]).unwrap().names(), ["web", "worker"]);
        assert_eq!(Roles::from_names::<&str>(&[]).unwrap(), Roles::default());
        let e = Roles::from_names(&["web", "edge"]).unwrap_err();
        assert_eq!(e, "unknown role \"edge\": the roles are web and worker");

        let mut cfg = Config::parse("[server]\nroles = [\"worker\"]\n").unwrap();
        assert_eq!(cfg.roles().unwrap().names(), ["worker"]);
        cfg.apply_env(|k| (k == "OXYHUB_SERVER_ROLES").then(|| "web, worker".into()));
        assert_eq!(cfg.roles().unwrap(), Roles::default());
        cfg.apply_env(|k| (k == "OXYHUB_SERVER_ROLES").then(|| "store".into()));
        assert!(cfg.roles().unwrap_err().to_string().contains("unknown role \"store\""));
    }

    #[test]
    fn an_unknown_role_in_hub_toml_stops_loading() {
        let dir = tempfile::tempdir().unwrap();
        std::fs::write(dir.path().join("hub.toml"), "[server]\nroles = [\"wrker\"]\n").unwrap();
        let e = Config::load(dir.path()).unwrap_err().to_string();
        assert!(e.contains("unknown role \"wrker\""), "{e}");
    }
}
`/`	Search
`g` `c`	Code
`g` `h`	History
`g` `b`	Bookmarks
`g` `t`	Trust
`y`	Permalink to this state (files and trees)
`?`	This sheet
Keyboard
