clawhdf5/crates/clawhdf5-tools/tests/remote.rs

//! `h5rs` on URLs (feature `remote`): every subcommand prints for
//! `http://…/file.h5` what it prints for the local file (the name aside).
//! The files are served by the range-request test server of
//! clawhdf5-remote on 127.0.0.1.

#![cfg(feature = "remote")]

#[path = "../../clawhdf5-remote/tests/common/server.rs"]
mod server;

use std::path::{Path, PathBuf};
use std::process::Command;

fn h5rs(args: &[&str]) -> (String, i32) {
    let out = Command::new(env!("CARGO_BIN_EXE_h5rs"))
        .args(args)
        .output()
        .expect("run h5rs");
    let text = format!(
        "{}{}",
        String::from_utf8_lossy(&out.stdout),
        String::from_utf8_lossy(&out.stderr)
    );
    (text, out.status.code().unwrap_or(-1))
}

fn fixtures() -> Vec<PathBuf> {
    let root = Path::new(env!("CARGO_MANIFEST_DIR"));
    [
        "../clawhdf5/tests/fixtures/tall.h5",
        "../clawhdf5/tests/fixtures/written_by_v2_7_0.h5",
        "../clawhdf5/tests/fixtures/written_by_v2_7_0_paged.h5",
        "../clawhdf5/tests/fixtures/h5clear_mdc_image.h5",
        "../clawhdf5-format/tests/fixtures/fractal_heap_multiblock.h5",
        "../clawhdf5-format/tests/fixtures/legacy/tcompound.h5",
        "../clawhdf5-format/tests/fixtures/legacy/h5ex_g_iterate.h5",
    ]
    .iter()
    .map(|p| root.join(p))
    .collect()
}

#[test]
fn every_subcommand_reads_a_url_like_the_local_file() {
    let files = fixtures();
    let served: Vec<(String, Vec<u8>)> = files
        .iter()
        .enumerate()
        .map(|(i, p)| {
            let name = p.file_name().unwrap().to_str().unwrap();
            (format!("/{i}/{name}"), std::fs::read(p).unwrap())
        })
        .collect();
    let server = server::Server::start(served.clone());
    for (p, (url_path, _)) in files.iter().zip(&served) {
        let url = server.url(url_path);
        let local = p.to_str().unwrap();
        for cmd in [
            &["ls", "-r", "-v"][..],
            &["dump"],
            &["dump", "--json"],
            &["stat"],
            &["check", "--data"],
        ] {
            fn args<'a>(cmd: &[&'a str], f: &'a str) -> Vec<&'a str> {
                cmd.iter().copied().chain([f]).collect()
            }
            let (want, want_rc) = h5rs(&args(cmd, local));
            let (got, got_rc) = h5rs(&args(cmd, &url));
            assert_eq!(
                got.replace(&url, local),
                want,
                "h5rs {} {url}",
                cmd.join(" ")
            );
            assert_eq!(got_rc, want_rc, "h5rs {} {url}", cmd.join(" "));
        }
        let (a, rc) = h5rs(&["diff", local, &url]);
        assert_eq!(rc, 0, "h5rs diff {local} {url}: {a}");
    }
}

#[test]
fn url_errors_are_clean() {
    let server = server::Server::start(vec![("/x.h5".into(), vec![1u8; 100])]);
    let (out, rc) = h5rs(&["ls", &server.url("/missing.h5")]);
    assert_eq!(rc, 2, "{out}");
    assert!(out.contains("404"), "{out}");
    let (out, rc) = h5rs(&["ls", &server.url("/x.h5")]);
    assert_eq!(rc, 2, "{out}");
    assert!(out.contains("not an HDF5 file"), "{out}");
    let (out, rc) = h5rs(&["check", &server.url("/missing.h5")]);
    assert_eq!(rc, 2, "{out}");
    #[cfg(not(feature = "remote-https"))]
    {
        let (out, rc) = h5rs(&["ls", "https://example.com/a.h5"]);
        assert_eq!(rc, 2, "{out}");
        assert!(out.contains("`https` feature"), "{out}");
    }
}

/// `check` downloads a remote file whole, but never trusts the length the
/// server claims: a server claiming 2^62 bytes for a small file is refused
/// before anything is allocated (it used to abort the process), and
/// `--max-download` caps real files too.
#[test]
fn check_refuses_a_remote_file_beyond_the_download_limit() {
    use std::sync::atomic::Ordering;
    let tall = Path::new(env!("CARGO_MANIFEST_DIR")).join("../clawhdf5/tests/fixtures/tall.h5");
    let server = server::Server::start(vec![("/t.h5".into(), std::fs::read(&tall).unwrap())]);
    let url = server.url("/t.h5");
    let (out, rc) = h5rs(&["check", &url]);
    assert_eq!(rc, 0, "{out}");
    let (out, rc) = h5rs(&["check", "--max-download", "1000", &url]);
    assert_eq!(rc, 2, "{out}");
    assert!(out.contains("download limit of 1000 bytes"), "{out}");
    server.shared.fake_total.store(1 << 62, Ordering::SeqCst);
    let (out, rc) = h5rs(&["check", &url]);
    assert_eq!(rc, 2, "{out}");
    assert!(out.contains("more than the download limit"), "{out}");
}

/// A URL's credentials (userinfo, a presigned URL's query string) are not
/// printed: not in errors, not in the file name of the output.
#[test]
fn credentials_in_urls_are_not_printed() {
    let tall = Path::new(env!("CARGO_MANIFEST_DIR")).join("../clawhdf5/tests/fixtures/tall.h5");
    let server = server::Server::start(vec![("/t.h5".into(), std::fs::read(&tall).unwrap())]);
    let url = |path: &str| {
        format!(
            "http://user:hunter2@{}{path}?X-Amz-Signature=SECRETSIG",
            server.addr
        )
    };
    for args in [
        vec!["ls", "-r"],
        vec!["dump"],
        vec!["stat"],
        vec!["check"],
        vec!["check", "--max-download", "10"],
    ] {
        for path in ["/t.h5", "/missing.h5"] {
            let u = url(path);
            let mut a = args.clone();
            a.push(&u);
            let (out, _) = h5rs(&a);
            assert!(
                !out.contains("hunter2") && !out.contains("SECRETSIG"),
                "h5rs {}: {out}",
                a.join(" ")
            );
        }
    }
    let (out, rc) = h5rs(&["diff", tall.to_str().unwrap(), &url("/t.h5"), "/nope"]);
    assert_eq!(rc, 2, "{out}");
    assert!(
        !out.contains("hunter2") && !out.contains("SECRETSIG"),
        "{out}"
    );
}