ipx/crates/directory/src/site.rs

//! The directory in a web browser (#215): anyone may browse it, no token, read only. The most
//! subscribed and the categories, every feed A to Z, a search by name, and a page per feed with
//! its address to subscribe to in any podcast app. Rendered here from the store, as plain HTML:
//! no build step, and nothing the API does not already hold.
//!
//! A feed's description and items are the publisher's HTML, unsanitized in the store; they are
//! shown as text, tags stripped, and an item's link only when it is http(s).

use std::collections::BTreeMap;
use std::fmt::Write;

use axum::extract::{Path, Query, State};
use axum::http::{HeaderValue, StatusCode, header};
use axum::response::{IntoResponse, Response};
use axum::routing::get;
use axum::Router;

use crate::{Listing, Shared};

pub fn router() -> Router<Shared> {
    Router::new()
        .route("/", get(home))
        .route("/all", get(all))
        .route("/search", get(search))
        .route("/category/{name}", get(category))
        .route("/feed/{id}", get(feed))
        .route("/site.css", get(|| asset("text/css; charset=utf-8", include_bytes!("site.css"))))
        .route("/site.js", get(|| asset("text/javascript; charset=utf-8", include_bytes!("site.js"))))
        .route("/logo.svg", get(|| asset("image/svg+xml", include_bytes!("../../../web/logo.svg"))))
        .route("/logo-dark.svg", get(|| asset("image/svg+xml", include_bytes!("../../../web/logo-dark.svg"))))
        .route("/favicon.png", get(|| asset("image/png", include_bytes!("../../../web/favicon.png"))))
}

/// Its own script and stylesheet only; covers come from their publishers.
const CSP: &str = "default-src 'none'; img-src https: http: data:; style-src 'self'; script-src 'self'; \
                   base-uri 'none'; form-action 'self'; frame-ancestors 'none'";

async fn asset(kind: &'static str, body: &'static [u8]) -> Response {
    ([(header::CONTENT_TYPE, kind), (header::CACHE_CONTROL, "public, max-age=86400")], body).into_response()
}

#[derive(serde::Deserialize, Default)]
struct Filter {
    /// `podcasts` or `blogs`; anything else is both.
    kind: Option<String>,
    sub: Option<String>,
    q: Option<String>,
}

impl Filter {
    fn keep(&self, l: &Listing) -> bool {
        match self.kind.as_deref() {
            Some("podcasts") => l.podcast,
            Some("blogs") => !l.podcast,
            _ => true,
        }
    }
}

async fn home(State(dir): State<Shared>) -> Response {
    let all = match dir.store.list().await {
        Ok(a) => a,
        Err(e) => return failed(e),
    };
    let mut top = all.clone();
    top.sort_by(|a, b| b.subscribers.cmp(&a.subscribers).then_with(|| name(a).to_lowercase().cmp(&name(b).to_lowercase())));
    top.truncate(10);
    let mut cats: BTreeMap<&str, Vec<&Listing>> = BTreeMap::new();
    for l in &all {
        cats.entry(l.category.as_deref().unwrap_or("Other")).or_default().push(l);
    }
    let mut b = String::new();
    if all.is_empty() {
        b.push_str("<p class=hint>Nothing is listed yet. A feed appears once a server has shared it and the directory has read it.</p>");
    } else {
        b.push_str("<h2>Most subscribed</h2><ol class=chart>");
        for (i, l) in top.iter().enumerate() {
            let _ = write!(b, "<li><a href=\"/feed/{}\"><span class=no>{}</span>{}<span class=txt><b>{}</b><small>{}</small></span></a></li>",
                esc(&l.id), i + 1, art(l, "art sm"), esc(name(l)), subscribers(l.subscribers));
        }
        b.push_str("</ol><h2>Categories</h2><div class=cats>");
        for (c, ls) in &cats {
            let _ = write!(b, "<a class=cat href=\"/category/{}\"><b>{}</b><small>{}</small></a>", seg(c), esc(c), ls.len());
        }
        let _ = write!(b, "</div><p><a class=more href=\"/all\">All {} feeds, A to Z</a></p>", all.len());
    }
    page("iPX Directory", None, &b)
}

async fn all(State(dir): State<Shared>, Query(f): Query<Filter>) -> Response {
    listed(&dir, "All feeds", "/all", &f, |_| true).await
}

async fn search(State(dir): State<Shared>, Query(f): Query<Filter>) -> Response {
    let q = f.q.clone().unwrap_or_default().trim().to_lowercase();
    if q.is_empty() {
        return redirect("/all");
    }
    let title = format!("Results for \u{201c}{}\u{201d}", f.q.as_deref().unwrap_or("").trim());
    listed(&dir, &title, "/search", &f, move |l| name(l).to_lowercase().contains(&q)).await
}

async fn category(State(dir): State<Shared>, Path(c): Path<String>, Query(f): Query<Filter>) -> Response {
    let here = format!("/category/{}", seg(&c));
    let cat = c.clone();
    listed(&dir, &c, &here, &f, move |l| l.category.as_deref().unwrap_or("Other") == cat).await
}

/// A page of tiles: those `pick` takes, of the kind and subcategory asked for, A to Z.
async fn listed(dir: &Shared, title: &str, here: &str, f: &Filter, pick: impl Fn(&Listing) -> bool) -> Response {
    let mut ls: Vec<Listing> = match dir.store.list().await {
        Ok(a) => a.into_iter().filter(|l| pick(l)).collect(),
        Err(e) => return failed(e),
    };
    if ls.is_empty() && here.starts_with("/category/") {
        return not_found("That category has nothing in it.");
    }
    let subs: BTreeMap<String, usize> = ls.iter().filter_map(|l| l.subcategory.clone()).fold(BTreeMap::new(), |mut m, s| {
        *m.entry(s).or_default() += 1;
        m
    });
    ls.retain(|l| f.keep(l) && f.sub.as_ref().is_none_or(|s| l.subcategory.as_ref() == Some(s)));
    ls.sort_by_key(|l| name(l).to_lowercase());

    // The query a link keeps, with one of its keys changed.
    let link = |kind: Option<&str>, sub: Option<&str>| {
        let mut q = url::form_urlencoded::Serializer::new(String::new());
        if let Some(v) = f.q.as_deref() {
            q.append_pair("q", v);
        }
        if let Some(v) = kind {
            q.append_pair("kind", v);
        }
        if let Some(v) = sub {
            q.append_pair("sub", v);
        }
        let q = q.finish();
        if q.is_empty() { here.to_owned() } else { format!("{here}?{q}") }
    };
    let mut b = String::new();
    let _ = write!(b, "<p class=back><a href=\"/\">Directory</a></p><h2>{}</h2><nav class=tabs aria-label=Kind>", esc(title));
    for (k, label) in [(None, "All"), (Some("podcasts"), "Podcasts"), (Some("blogs"), "Blogs")] {
        let on = f.kind.as_deref() == k;
        let _ = write!(b, "<a href=\"{}\"{}>{label}</a>", esc(&link(k, f.sub.as_deref())), if on { " aria-current=page" } else { "" });
    }
    b.push_str("</nav>");
    if !subs.is_empty() {
        b.push_str("<nav class=pills aria-label=Subcategory>");
        let _ = write!(b, "<a href=\"{}\"{}>All</a>", esc(&link(f.kind.as_deref(), None)), if f.sub.is_none() { " aria-current=page" } else { "" });
        for (s, n) in &subs {
            let on = f.sub.as_deref() == Some(s.as_str());
            let _ = write!(b, "<a href=\"{}\"{}>{} <small>{n}</small></a>", esc(&link(f.kind.as_deref(), Some(s))), if on { " aria-current=page" } else { "" }, esc(s));
        }
        b.push_str("</nav>");
    }
    if ls.is_empty() {
        b.push_str("<p class=hint>Nothing here.</p>");
    } else {
        let _ = write!(b, "<p class=count>{}</p><div class=tiles>", plural(ls.len(), "feed"));
        for l in &ls {
            let _ = write!(b, "<a class=tile href=\"/feed/{}\">{}<b>{}</b><small>{}</small></a>", esc(&l.id), art(l, "art"), esc(name(l)), subscribers(l.subscribers));
        }
        b.push_str("</div>");
    }
    page(title, None, &b)
}

async fn feed(State(dir): State<Shared>, Path(id): Path<String>) -> Response {
    let p = match dir.store.feed(&id).await {
        Ok(Some(p)) => p,
        Ok(None) => return not_found("That feed is not in the directory."),
        Err(e) => return failed(e),
    };
    let l = &p.listing;
    let mut b = String::new();
    b.push_str("<p class=back><a href=\"/\">Directory</a>");
    if let Some(c) = &l.category {
        let _ = write!(b, " <span aria-hidden=true>/</span> <a href=\"/category/{}\">{}</a>", seg(c), esc(c));
    }
    let _ = write!(b, "</p><div class=show>{}<div class=meta><h2>{}</h2><p class=sub>{}{}</p>", art(l, "art lg"), esc(name(l)),
        subscribers(l.subscribers), l.subcategory.as_deref().map(|s| format!(" &middot; {}", esc(s))).unwrap_or_default());
    let _ = write!(b, "<div class=addr><label for=addr>Feed address</label><span class=row><input id=addr readonly value=\"{}\" spellcheck=false>\
        <button type=button data-copy=\"{}\">Copy</button></span><small>Paste it into any podcast app or feed reader to subscribe.</small></div></div></div>",
        esc(&l.url), esc(&l.url));
    if let Some(d) = p.description.as_deref().map(text).filter(|d| !d.is_empty() && d != name(l)) {
        let _ = write!(b, "<p class=about>{}</p>", esc(&d));
    }
    if let Some(why) = &p.failing {
        let _ = write!(b, "<p class=failing>{}</p>", esc(why));
    }
    let _ = write!(b, "<h3>{}</h3>", if l.podcast { "Latest episodes" } else { "Latest posts" });
    if p.items.is_empty() {
        b.push_str("<p class=hint>Nothing read from it yet. The directory checks each feed every six hours.</p>");
    }
    for e in &p.items {
        let title = e.title.as_deref().map(text).filter(|t| !t.is_empty()).unwrap_or_else(|| "Untitled".into());
        let head = match e.link.as_deref().filter(|u| u.starts_with("https://") || u.starts_with("http://")) {
            Some(u) => format!("<a href=\"{}\" rel=\"noopener nofollow\">{}</a>", esc(u), esc(&title)),
            None => esc(&title),
        };
        let blurb: String = e.description.as_deref().map(text).unwrap_or_default().chars().take(400).collect();
        let when = [e.published.map(date), e.duration.filter(|d| *d > 0).map(clock)].into_iter().flatten().collect::<Vec<_>>().join(" &middot; ");
        let _ = write!(b, "<article><b>{head}</b>{}{}</article>",
            if blurb.is_empty() { String::new() } else { format!("<p>{}</p>", esc(&blurb)) },
            if when.is_empty() { String::new() } else { format!("<small>{when}</small>") });
    }
    page(name(l), Some(&text(p.description.as_deref().unwrap_or(""))), &b)
}

fn page(title: &str, description: Option<&str>, body: &str) -> Response {
    let full = if title == "iPX Directory" { title.to_owned() } else { format!("{title} | iPX Directory") };
    let desc = description.filter(|d| !d.is_empty()).map(|d| d.chars().take(200).collect::<String>())
        .unwrap_or_else(|| "Public podcasts and blogs that iPX servers share.".into());
    let html = format!(
        "<!doctype html><html lang=en><head><meta charset=utf-8><meta name=viewport content=\"width=device-width,initial-scale=1\">\
         <title>{}</title><meta name=description content=\"{}\"><meta name=color-scheme content=\"light dark\">\
         <link rel=icon href=/favicon.png><link rel=stylesheet href=/site.css><script src=/site.js defer></script></head>\
         <body><header><a class=brand href=\"/\"><picture><source srcset=/logo-dark.svg media=\"(prefers-color-scheme: dark)\">\
         <img src=/logo.svg alt=\"\" width=32 height=32></picture>iPX Directory</a>\
         <form action=/search role=search><input type=search name=q placeholder=\"Find a feed\" aria-label=\"Find a feed by name\"></form></header>\
         <main>{body}</main><footer>Public podcasts and blogs that iPX servers share, and how many people on them subscribe. \
         Read only: to change what is here, an iPX server shares its public feeds.</footer></body></html>",
        esc(&full),
        esc(&desc),
    );
    let mut r = html.into_response();
    let h = r.headers_mut();
    h.insert(header::CONTENT_TYPE, HeaderValue::from_static("text/html; charset=utf-8"));
    h.insert(header::CACHE_CONTROL, HeaderValue::from_static("public, max-age=300"));
    h.insert(header::CONTENT_SECURITY_POLICY, HeaderValue::from_static(CSP));
    h.insert("x-content-type-options", HeaderValue::from_static("nosniff"));
    h.insert("referrer-policy", HeaderValue::from_static("no-referrer"));
    r
}

fn not_found(why: &str) -> Response {
    let mut r = page("Not found", None, &format!("<p class=back><a href=\"/\">Directory</a></p><h2>Not found</h2><p class=hint>{}</p>", esc(why)));
    *r.status_mut() = StatusCode::NOT_FOUND;
    r
}

fn failed(e: anyhow::Error) -> Response {
    tracing::error!(error = %format!("{e:#}"), "a directory page failed");
    let mut r = page("Unavailable", None, "<h2>Unavailable</h2><p class=hint>The directory could not read its list just now. Try again in a minute.</p>");
    *r.status_mut() = StatusCode::SERVICE_UNAVAILABLE;
    r
}

fn redirect(to: &'static str) -> Response {
    (StatusCode::SEE_OTHER, [(header::LOCATION, to)]).into_response()
}

/// A cover from its publisher, over the feed's initials, which show where it has none or it fails.
fn art(l: &Listing, class: &str) -> String {
    // The first letter of each of the first two words that have one: `<antirez>` is A, not nothing.
    let initials: String = name(l).split_whitespace().filter_map(|w| w.chars().find(|c| c.is_alphanumeric())).take(2).collect();
    let img = l.image.as_deref().filter(|u| u.starts_with("https://") || u.starts_with("http://"))
        .map(|u| format!("<img src=\"{}\" alt=\"\" loading=lazy referrerpolicy=no-referrer>", esc(u)))
        .unwrap_or_default();
    format!("<span class=\"{class}\" aria-hidden=true><i>{}</i>{img}</span>", esc(&initials.to_uppercase()))
}

fn name(l: &Listing) -> &str {
    l.title.as_deref().filter(|t| !t.trim().is_empty()).unwrap_or(&l.id)
}

fn subscribers(n: i64) -> String {
    match n {
        0 => "Listed, no subscribers yet".into(),
        1 => "1 person subscribes".into(),
        n => format!("{n} people subscribe"),
    }
}

fn plural(n: usize, word: &str) -> String {
    format!("{n} {word}{}", if n == 1 { "" } else { "s" })
}

/// `12 Oct 2026`, from a Unix time, with no date library: the civil-from-days algorithm.
fn date(t: i64) -> String {
    let z = t.div_euclid(86_400) + 719_468;
    let era = z.div_euclid(146_097);
    let doe = z - era * 146_097;
    let yoe = (doe - doe / 1460 + doe / 36_524 - doe / 146_096) / 365;
    let doy = doe - (365 * yoe + yoe / 4 - yoe / 100);
    let mp = (5 * doy + 2) / 153;
    let d = doy - (153 * mp + 2) / 5 + 1;
    let m = if mp < 10 { mp + 3 } else { mp - 9 };
    let y = yoe + era * 400 + i64::from(m <= 2);
    const MONTHS: [&str; 12] = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"];
    format!("{d} {} {y}", MONTHS[(m - 1) as usize])
}

fn clock(secs: i64) -> String {
    let (h, m) = (secs / 3600, secs % 3600 / 60);
    if h > 0 { format!("{h} h {m} min") } else { format!("{} min", m.max(1)) }
}

/// The publisher's HTML as plain text: tags gone, entities read, whitespace collapsed. Escaped
/// again where it is shown.
fn text(html: &str) -> String {
    // A space where each tag was, or two paragraphs run together: "drives.For over".
    let stripped = ammonia::Builder::empty().clean(&html.replace('<', " <")).to_string();
    let decoded = stripped.replace("&lt;", "<").replace("&gt;", ">").replace("&quot;", "\"").replace("&#39;", "'").replace("&nbsp;", " ").replace("&amp;", "&");
    decoded.split_whitespace().collect::<Vec<_>>().join(" ")
}

fn esc(s: &str) -> String {
    let mut out = String::with_capacity(s.len());
    for c in s.chars() {
        match c {
            '&' => out.push_str("&amp;"),
            '<' => out.push_str("&lt;"),
            '>' => out.push_str("&gt;"),
            '"' => out.push_str("&quot;"),
            '\'' => out.push_str("&#39;"),
            c => out.push(c),
        }
    }
    out
}

/// A category as a path segment.
fn seg(s: &str) -> String {
    percent_encoding::utf8_percent_encode(s, percent_encoding::NON_ALPHANUMERIC).to_string()
}

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

    #[test]
    fn the_publishers_html_becomes_text_and_is_escaped_where_shown() {
        assert_eq!(text("<p>Tom &amp; Jerry <script>alert(1)</script><b>live</b></p>"), "Tom & Jerry live");
        assert_eq!(text("<p>One.</p><p>Two.</p>"), "One. Two.");
        assert_eq!(esc(&text("a &lt;b&gt; c")), "a &lt;b&gt; c");
        assert_eq!(esc("\"><img onerror=x>"), "&quot;&gt;&lt;img onerror=x&gt;");
    }

    #[test]
    fn dates_and_lengths_read_as_people_write_them() {
        assert_eq!(date(0), "1 Jan 1970");
        assert_eq!(date(1_791_820_800), "12 Oct 2026");
        assert_eq!(date(951_782_400), "29 Feb 2000");
        assert_eq!(clock(59), "1 min");
        assert_eq!(clock(3_725), "1 h 2 min");
    }
}