portal/src/bin/question_lint.rs

//! Headless schema-check binary - loads content and `aggregates.yaml`
//! (from a Gitea repo URL or a local directory) and validates them
//! exactly the way `content::watch_for_reload`/`main.rs`'s boot path
//! do, with no NATS, OIDC, web server, or JetStream connection
//! involved. Built once by portal's own deploy workflow and run
//! directly by `questions`' own CI (same bare-metal runner/host,
//! published to a stable path - no artifact download needed), rather
//! than compiled there - keeps that repo's CI coupling to "run a
//! static binary," not "build a Rust workspace."
#![cfg(feature = "ssr")]

use portal::{aggregates, content};

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let mut args = std::env::args().skip(1);
    let mut repo: Option<String> = None;
    let mut branch = "main".to_string();
    let mut subdir = "questions".to_string();
    let mut path: Option<String> = None;

    while let Some(arg) = args.next() {
        match arg.as_str() {
            "--repo" => repo = args.next(),
            "--branch" => branch = args.next().unwrap_or(branch),
            "--subdir" => subdir = args.next().unwrap_or(subdir),
            "--path" => path = args.next(),
            other => {
                eprintln!("unknown argument: {other}");
                std::process::exit(2);
            }
        }
    }

    let (questions, aggregates_map, site) = if let Some(dir) = path {
        (load_from_dir(&dir)?, load_aggregates_from_dir(&dir)?, load_site_from_dir(&dir)?)
    } else if let Some(repo_url) = repo {
        let questions = content::load_questions_from_gitea(&repo_url, &branch, &subdir).await?;
        let aggregates_map = content::load_aggregates_from_gitea(&repo_url, &branch).await?;
        // load_site_from_gitea already validates; a missing file is
        // the default config, same as at portal boot.
        let site = content::load_site_from_gitea(&repo_url, &branch).await?;
        (questions, aggregates_map, site)
    } else {
        eprintln!(
            "usage: question-lint --repo <gitea-url> [--branch main] [--subdir questions] | --path <local-dir>"
        );
        std::process::exit(2);
    };

    if let Err(e) = site.validate() {
        eprintln!("FAIL: {e}");
        std::process::exit(1);
    }
    match content::validate_questions(&questions, &aggregates_map) {
        Ok(()) => {
            println!(
                "OK: {} question(s), {} aggregate(s) valid",
                questions.len(),
                aggregates_map.len()
            );
            Ok(())
        }
        Err(e) => {
            eprintln!("FAIL: {e}");
            std::process::exit(1);
        }
    }
}

/// The offline counterpart to `content::load_site_from_gitea` -
/// `site.yaml` lives at the repo root like `aggregates.yaml`, and is
/// just as optional locally: missing means default branding.
fn load_site_from_dir(dir: &str) -> anyhow::Result<content::SiteConfig> {
    let site_path = std::path::Path::new(dir)
        .parent()
        .unwrap_or_else(|| std::path::Path::new("."))
        .join("site.yaml");
    if !site_path.exists() {
        return Ok(content::SiteConfig::default());
    }
    let raw = std::fs::read_to_string(&site_path)
        .map_err(|e| anyhow::anyhow!("reading {}: {e}", site_path.display()))?;
    serde_yaml::from_str(&raw).map_err(|e| anyhow::anyhow!("parsing {}: {e}", site_path.display()))
}

/// The offline counterpart to `content::load_aggregates_from_gitea` -
/// `aggregates.yaml` lives at the repo root, one level up from the
/// pages directory `--path` names, so `dir`'s parent is where it's
/// looked for. Missing entirely is not an error here (unlike
/// `--repo` mode, where `aggregates.yaml` is required) - a local
/// checkout being linted may not have one, and every declared
/// transition still gets checked against whatever *is* found; an
/// empty map just means nothing is checked.
fn load_aggregates_from_dir(
    dir: &str,
) -> anyhow::Result<std::collections::HashMap<String, aggregates::AggregateSchema>> {
    let aggregates_path = std::path::Path::new(dir)
        .parent()
        .unwrap_or_else(|| std::path::Path::new("."))
        .join("aggregates.yaml");
    if !aggregates_path.exists() {
        return Ok(std::collections::HashMap::new());
    }
    let raw = std::fs::read_to_string(&aggregates_path)
        .map_err(|e| anyhow::anyhow!("reading {}: {e}", aggregates_path.display()))?;
    aggregates::parse_aggregates_yaml(&raw)
}

/// The offline counterpart to `content::load_questions_from_gitea` -
/// the same recursive tree walk and `content::build_questions`
/// pipeline (derived ids, relative refs, sections, followup
/// inference), just reading a local checkout instead of Gitea's API,
/// for linting a branch that hasn't been pushed yet.
fn load_from_dir(
    dir: &str,
) -> anyhow::Result<std::collections::HashMap<String, content::Question>> {
    let base = std::path::Path::new(dir);
    let mut files = Vec::new();
    collect_yaml(base, base, &mut files)?;
    content::build_questions(&files)
}

fn collect_yaml(
    base: &std::path::Path,
    dir: &std::path::Path,
    out: &mut Vec<(String, String)>,
) -> anyhow::Result<()> {
    for entry in std::fs::read_dir(dir)? {
        let path = entry?.path();
        if path.is_dir() {
            collect_yaml(base, &path, out)?;
        } else if path.extension().and_then(|e| e.to_str()) == Some("yaml") {
            let rel = path
                .strip_prefix(base)
                .expect("walked paths sit under their base")
                .to_string_lossy()
                .replace('\\', "/");
            let raw = std::fs::read_to_string(&path)
                .map_err(|e| anyhow::anyhow!("reading {}: {e}", path.display()))?;
            out.push((rel, raw));
        }
    }
    Ok(())
}