ipx/src/art.rs

//! Artwork kept on disk, so the page loads it from iPX: fast after the first time, nothing asked
//! of each publisher's server for every visit, and still there when a publisher is not.

use std::path::{Path, PathBuf};
use std::collections::HashMap;
use std::sync::{LazyLock, Mutex};
use std::time::{Duration, Instant};

pub fn dir() -> PathBuf {
    crate::config::data_dir().join("art")
}

/// Where an image's bytes are kept; its content type is beside it, in `<name>.type`.
// ponytail: std's hasher, 64 bits, keyed by the URL. Its algorithm may change with Rust, which
// only makes the cache miss once and refill; a collision among a few thousand images is about
// one in 10^12. Move to a SHA if either ever matters.
pub fn path(url: &str) -> PathBuf {
    use std::hash::{Hash, Hasher};
    let mut h = std::collections::hash_map::DefaultHasher::new();
    url.hash(&mut h);
    dir().join(format!("{:016x}", h.finish()))
}

/// A kept image and its type, marked as just used, which is what keeps it from being trimmed.
pub fn read(file: &Path) -> Option<(String, Vec<u8>)> {
    let kind = std::fs::read_to_string(file.with_extension("type")).ok()?;
    let body = std::fs::read(file).ok()?;
    if let Ok(f) = std::fs::File::options().write(true).open(file) {
        let _ = f.set_modified(std::time::SystemTime::now());
    }
    Some((kind, body))
}

/// Keeps an image, written aside and renamed into place, so a page asking for it meanwhile
/// never reads half of one.
pub fn write(file: &Path, kind: &str, body: &[u8]) -> std::io::Result<()> {
    std::fs::create_dir_all(file.parent().unwrap_or(Path::new(".")))?;
    let tmp = file.with_extension("part");
    std::fs::write(&tmp, body)?;
    std::fs::write(file.with_extension("type"), kind)?;
    std::fs::rename(&tmp, file)
}

/// How long an address that could not be fetched is answered from memory before it is tried again.
const RETRY: Duration = Duration::from_secs(60 * 60);

/// Addresses that could not be fetched lately, and why. Without it a page shown again fetched
/// them again: five covers too big to keep were downloaded from Patreon on every load (#169).
// ponytail: in memory, and an entry goes only when it is asked for after RETRY. It holds at most
// one per artwork address a feed or item names; move it to disk or prune it on trim if that grows.
static FAILED: LazyLock<Mutex<HashMap<String, (Instant, String)>>> = LazyLock::new(Default::default);

/// Why `url` could not be fetched, if it failed less than an hour ago.
pub fn failed(url: &str) -> Option<String> {
    failed_as_of(url, Instant::now())
}

fn failed_as_of(url: &str, now: Instant) -> Option<String> {
    let mut map = FAILED.lock().unwrap_or_else(|e| e.into_inner());
    match map.get(url) {
        Some((at, why)) if now.duration_since(*at) < RETRY => Some(why.clone()),
        Some(_) => {
            map.remove(url);
            None
        }
        None => None,
    }
}

pub fn fail(url: &str, why: &str) {
    FAILED.lock().unwrap_or_else(|e| e.into_inner()).insert(url.to_owned(), (Instant::now(), why.to_owned()));
}

/// Removes the least recently used images until what is kept fits in `limit` bytes; 0 empties it.
/// Returns how many went.
pub fn trim(dir: &Path, limit: u64) -> usize {
    let Ok(entries) = std::fs::read_dir(dir) else { return 0 };
    let mut kept: Vec<(std::time::SystemTime, u64, PathBuf)> = entries
        .flatten()
        .map(|e| e.path())
        .filter(|p| p.extension().is_none())
        .filter_map(|p| {
            let m = p.metadata().ok()?;
            Some((m.modified().ok()?, m.len(), p))
        })
        .collect();
    let mut total: u64 = kept.iter().map(|(_, n, _)| n).sum();
    kept.sort();
    let mut gone = 0;
    for (_, n, p) in kept {
        if total <= limit {
            break;
        }
        let _ = std::fs::remove_file(p.with_extension("type"));
        if std::fs::remove_file(&p).is_ok() {
            total -= n;
            gone += 1;
        }
    }
    crate::metrics::STATS.art_cache_bytes.store(total, std::sync::atomic::Ordering::Relaxed);
    crate::metrics::STATS.art_evicted.fetch_add(gone as u64, std::sync::atomic::Ordering::Relaxed);
    gone
}

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

    #[test]
    fn the_least_recently_used_go_first_until_it_fits() {
        let d = std::env::temp_dir().join(format!("ipx-art-test-{}", std::process::id()));
        let _ = std::fs::remove_dir_all(&d);
        for (name, age) in [("old", 300), ("mid", 200), ("new", 100)] {
            let f = d.join(name);
            write(&f, "image/png", &[0; 1000]).unwrap();
            let t = std::time::SystemTime::now() - std::time::Duration::from_secs(age);
            std::fs::File::options().write(true).open(&f).unwrap().set_modified(t).unwrap();
        }
        // Shown just now: no longer the oldest.
        assert_eq!(read(&d.join("old")).unwrap().0, "image/png");
        assert_eq!(trim(&d, 2000), 1);
        assert!(!d.join("mid").exists() && !d.join("mid.type").exists());
        assert!(d.join("old").exists() && d.join("new").exists());
        assert_eq!(trim(&d, 0), 2);
        let _ = std::fs::remove_dir_all(&d);
    }

    #[test]
    fn a_failure_is_remembered_for_an_hour() {
        let u = "https://example.com/a-failure-is-remembered.png";
        assert_eq!(failed(u), None);
        fail(u, "larger than 5 MB");
        assert_eq!(failed(u).as_deref(), Some("larger than 5 MB"));
        assert_eq!(failed_as_of(u, Instant::now() + RETRY), None);
        // Asked for after the hour, it is forgotten, not just ignored.
        assert_eq!(failed(u), None);
    }
}