clawhdf5/crates/clawhdf5-remote/tests/common/mod.rs

//! Shared by the integration tests: the test server, a transcript of a
//! file (tree, attributes, values) to compare two ways of reading it, and
//! the test files.

#![allow(dead_code)]

pub mod server;

use std::collections::{BTreeMap, HashSet, VecDeque};
use std::fmt::Write as _;
use std::path::{Path, PathBuf};
use std::process::Command;
use std::sync::Arc;

use clawhdf5::{DType, File, Selection};
use clawhdf5_format::error::FormatError;

/// Objects visited per file.
const MAX_OBJECTS: usize = 2000;
/// Datasets with more bytes than this are not read (their metadata is).
pub const MAX_DATA_BYTES: u64 = 64 << 20;

/// A short, stable digest of a value's `Debug` form.
fn digest<T: std::fmt::Debug>(v: &T) -> String {
    let s = format!("{v:?}");
    if s.len() <= 200 {
        return s;
    }
    let mut h = 0xcbf2_9ce4_8422_2325u64;
    for b in s.bytes() {
        h = (h ^ u64::from(b)).wrapping_mul(0x100_0000_01b3);
    }
    format!("{}…[{} bytes, fnv {h:016x}]", &s[..80], s.len())
}

/// A data read's value, or `Err` (which chunk a damaged dataset reports
/// can vary between two `File`s: the chunk cache lists in hash order).
fn value<T: std::fmt::Debug, E>(r: &Result<T, E>) -> String {
    match r {
        Ok(v) => digest(v),
        Err(_) => "Err".into(),
    }
}

fn sorted<V: std::fmt::Debug>(m: std::collections::HashMap<String, V>) -> BTreeMap<String, V> {
    m.into_iter().collect()
}

/// Everything a reader sees in `file`: every group's entries, every
/// object's attributes, and every dataset's shape, types and values.
pub fn transcript(file: &File) -> String {
    let mut out = String::new();
    let mut seen = HashSet::new();
    let mut queue = VecDeque::from([(String::from("/"), file.superblock().root_group_address)]);
    while let Some((path, addr)) = queue.pop_front() {
        if seen.len() >= MAX_OBJECTS || !seen.insert(addr) {
            continue;
        }
        let group = file.group_at(addr);
        let entries = group.entries();
        writeln!(out, "{path} @{addr} entries {}", digest(&entries)).unwrap();
        if let Ok(ds) = file.dataset_at(addr) {
            dataset(&mut out, &path, &ds);
        }
        let attrs = group.attrs_with_errors().map(|(a, e)| (sorted(a), e));
        writeln!(out, "{path} attrs {}", digest(&attrs)).unwrap();
        if let Ok(entries) = entries {
            for (name, child) in entries {
                queue.push_back((format!("{}/{name}", path.trim_end_matches('/')), child));
            }
        }
    }
    out
}

fn dataset(out: &mut String, path: &str, ds: &clawhdf5::Dataset<'_>) {
    let shape = ds.shape();
    let dtype = ds.dtype();
    writeln!(
        out,
        "{path} shape {} dtype {} raw {}",
        digest(&shape),
        digest(&dtype),
        digest(&ds.raw_datatype())
    )
    .unwrap();
    let (Ok(shape), Ok(dtype), Ok(raw_dt)) = (shape, dtype, ds.raw_datatype()) else {
        return;
    };
    let elements = shape.iter().try_fold(1u64, |a, &d| a.checked_mul(d));
    let bytes = elements.and_then(|n| n.checked_mul(u64::from(raw_dt.type_size())));
    if bytes.is_none_or(|b| b > MAX_DATA_BYTES) {
        writeln!(out, "{path} too large to read").unwrap();
        return;
    }
    writeln!(
        out,
        "{path} all {}",
        value(&ds.read_selection(&Selection::All))
    )
    .unwrap();
    if matches!(
        dtype,
        DType::F32
            | DType::F64
            | DType::I8
            | DType::I16
            | DType::I32
            | DType::I64
            | DType::U8
            | DType::U16
            | DType::U32
            | DType::U64
    ) {
        writeln!(out, "{path} f64 {}", value(&ds.read_f64())).unwrap();
        if let Some(&d0) = shape.first() {
            let rank = shape.len();
            let sel = Selection::Hyperslab {
                start: std::iter::once(d0 / 3)
                    .chain(std::iter::repeat_n(0, rank - 1))
                    .collect(),
                stride: vec![1; rank],
                count: std::iter::once(d0.div_ceil(3))
                    .chain(shape[1..].iter().copied())
                    .collect(),
                block: vec![1; rank],
            };
            writeln!(
                out,
                "{path} f64 third {}",
                value(&ds.read_f64_selection(&sel))
            )
            .unwrap();
        }
    }
    match &raw_dt {
        clawhdf5_format::datatype::Datatype::String { .. }
        | clawhdf5_format::datatype::Datatype::VariableLength {
            is_string: true, ..
        } => {
            writeln!(out, "{path} strings {}", value(&ds.read_string_bytes())).unwrap();
        }
        clawhdf5_format::datatype::Datatype::VariableLength { .. } => {
            writeln!(out, "{path} vlen {}", value(&ds.read_vlen::<f64>())).unwrap();
        }
        _ => {}
    }
}

/// Open, list every group, and read the first dataset found whose data is
/// at most `MAX_DATA_BYTES` (a tree view plus one plot).
pub fn list_and_read_one(file: &File) {
    let mut seen = HashSet::new();
    let mut read_one = false;
    let mut queue = VecDeque::from([file.superblock().root_group_address]);
    while let Some(addr) = queue.pop_front() {
        if seen.len() >= MAX_OBJECTS || !seen.insert(addr) {
            continue;
        }
        let group = file.group_at(addr);
        if let Ok(ds) = file.dataset_at(addr) {
            let _ = (ds.shape(), ds.dtype());
            if !read_one {
                let small = ds.shape().ok().and_then(|s| {
                    let n = s.iter().try_fold(1u64, |a, &d| a.checked_mul(d))?;
                    let size = u64::from(ds.raw_datatype().ok()?.type_size());
                    n.checked_mul(size).filter(|&b| b <= MAX_DATA_BYTES)
                });
                if small.is_some() {
                    let _ = ds.read_selection(&Selection::All);
                    read_one = true;
                }
            }
        }
        if let Ok(entries) = group.entries() {
            queue.extend(entries.into_iter().map(|(_, a)| a));
        }
    }
}

/// External virtual-dataset sources read from `dir`, as `File::open` finds
/// them next to the file.
pub fn sibling_resolver(dir: PathBuf) -> clawhdf5::VdsResolver {
    Arc::new(move |name: &str| {
        let p = Path::new(name);
        if name.is_empty()
            || !p
                .components()
                .all(|c| matches!(c, std::path::Component::Normal(_)))
        {
            return Err(FormatError::Storage(format!("{name:?} not followed")));
        }
        match std::fs::read(dir.join(p)) {
            Ok(bytes) => Ok(Some(bytes)),
            Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
            Err(e) => Err(FormatError::Storage(e.to_string())),
        }
    })
}

/// HDF5 files under `dir`, recursively.
pub fn hdf5_files(dir: &Path, out: &mut Vec<PathBuf>) {
    let Ok(entries) = std::fs::read_dir(dir) else {
        return;
    };
    for e in entries.flatten() {
        let p = e.path();
        if p.is_dir() {
            hdf5_files(&p, out);
        } else if p
            .extension()
            .and_then(|x| x.to_str())
            .is_some_and(|x| matches!(x, "h5" | "hdf5" | "he5" | "nc" | "h5ad" | "hdf"))
        {
            out.push(p);
        }
    }
}

/// The repository's HDF5 test fixtures.
pub fn fixtures() -> Vec<PathBuf> {
    let root = Path::new(env!("CARGO_MANIFEST_DIR"));
    let mut files = Vec::new();
    hdf5_files(&root.join("../clawhdf5/tests/fixtures"), &mut files);
    hdf5_files(&root.join("../clawhdf5-format/tests/fixtures"), &mut files);
    files.sort();
    files
}

/// Files of `CLAWHDF5_REMOTE_CORPUS` (directories separated like `PATH`).
pub fn corpus() -> Option<Vec<PathBuf>> {
    let dirs = std::env::var("CLAWHDF5_REMOTE_CORPUS").ok()?;
    let mut files = Vec::new();
    for d in std::env::split_paths(&dirs) {
        hdf5_files(&d, &mut files);
    }
    files.sort();
    Some(files)
}

pub fn python() -> String {
    std::env::var("CLAWHDF5_PYTHON").unwrap_or_else(|_| "python3".to_string())
}

pub fn interop_required() -> bool {
    std::env::var("CLAWHDF5_REQUIRE_INTEROP").is_ok_and(|v| v == "1")
}

/// Whether python3 with h5py and numpy runs; panics when interop is
/// required and it does not.
pub fn have_h5py() -> bool {
    let ok = Command::new(python())
        .args(["-c", "import h5py, numpy"])
        .output()
        .map(|o| o.status.success())
        .unwrap_or(false);
    assert!(
        ok || !interop_required(),
        "CLAWHDF5_REQUIRE_INTEROP=1 but python3 with h5py is not available"
    );
    if !ok {
        eprintln!("SKIP: python3 with h5py not available");
    }
    ok
}

/// Run a Python script; its stdout.
pub fn run_python(script: &str, args: &[&str]) -> String {
    let out = Command::new(python())
        .arg("-c")
        .arg(script)
        .args(args)
        .output()
        .expect("failed to run python");
    assert!(
        out.status.success(),
        "python failed:\n{}",
        String::from_utf8_lossy(&out.stderr)
    );
    String::from_utf8(out.stdout).unwrap()
}

/// A clawhdf5-written file with a multi-block chunked dataset (`/big`,
/// 1 000 000 f64 in chunks of 10 000, deflated), a contiguous one and a
/// group — several blocks of 1 MiB, with no Python needed.
pub fn multi_block_file() -> Vec<u8> {
    let mut b = clawhdf5::FileBuilder::new();
    b.set_attr("title", clawhdf5::AttrValue::String("remote test".into()));
    let big: Vec<f64> = (0..1_000_000u64)
        .map(|i| ((i * 2_654_435_761) % 1_000_003) as f64 * 0.5)
        .collect();
    b.create_dataset("big")
        .with_f64_data(&big)
        .with_chunks(&[10_000])
        .with_deflate(1);
    let flat: Vec<f64> = (0..300_000u64).map(|i| i as f64).collect();
    b.create_dataset("flat").with_f64_data(&flat);
    let mut g = b.create_group("grp");
    g.create_dataset("small").with_f64_data(&[1.0, 2.0, 3.0]);
    b.add_group(g.finish());
    b.finish().unwrap()
}