fix(format): convert float data read as integers instead of returning bit patterns

read_i32/read_i64/read_u64 on a floating-point dataset reinterpreted the
IEEE bits (1.5 read as i64 was 4609434218613702656). Convert like
libhdf5's hard conversions instead: truncate toward zero and saturate at
the target range; NaN reads as 0.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5/tests/numeric_conversion_interop.rs

@@ -0,0 +1,129 @@
+//! Numeric conversions on read, checked against h5py/libhdf5.
+//!
+//! h5py writes each file and prints what libhdf5 converts the data to
+//! (`Dataset.astype`); the typed readers must return the same values.
+//! Skipped when python3 with h5py is unavailable, unless
+//! `CLAWHDF5_REQUIRE_INTEROP=1`.
+
+use std::collections::HashMap;
+use std::process::Command;
+
+use clawhdf5::File;
+
+fn python() -> String {
+    std::env::var("CLAWHDF5_PYTHON").unwrap_or_else(|_| "python3".to_string())
+}
+
+fn interop_required() -> bool {
+    std::env::var("CLAWHDF5_REQUIRE_INTEROP").is_ok_and(|v| v == "1")
+}
+
+fn python_available() -> bool {
+    Command::new(python())
+        .args(["-c", "import h5py, numpy"])
+        .output()
+        .map(|o| o.status.success())
+        .unwrap_or(false)
+}
+
+macro_rules! skip_if_no_python {
+    () => {
+        if !python_available() {
+            assert!(
+                !interop_required(),
+                "CLAWHDF5_REQUIRE_INTEROP=1 but python3 with h5py is not available"
+            );
+            eprintln!("SKIP: python3 with h5py not available");
+            return;
+        }
+    };
+}
+
+/// Run `script` (which writes the file at `path`) and return its stdout as
+/// `key -> values`, one `key v1 v2 ...` line per key.
+fn run_python(script: &str) -> HashMap<String, Vec<String>> {
+    let output = Command::new(python())
+        .args(["-c", script])
+        .output()
+        .expect("failed to run python");
+    assert!(
+        output.status.success(),
+        "python failed:\n{}",
+        String::from_utf8_lossy(&output.stderr)
+    );
+    String::from_utf8_lossy(&output.stdout)
+        .lines()
+        .filter_map(|line| {
+            let mut words = line.split_whitespace().map(str::to_string);
+            Some((words.next()?, words.collect()))
+        })
+        .collect()
+}
+
+fn parse<T: std::str::FromStr>(values: &[String]) -> Vec<T>
+where
+    T::Err: std::fmt::Debug,
+{
+    values.iter().map(|v| v.parse().unwrap()).collect()
+}
+
+/// Python prelude: `emit(key, array)` prints one line of integers.
+const PRELUDE: &str = r#"
+import h5py, numpy as np
+def emit(key, arr):
+    print(key, *[int(v) for v in np.asarray(arr).ravel()])
+"#;
+
+#[test]
+fn float_dataset_read_as_integers_converts_like_libhdf5() {
+    // read_i32/read_i64/read_u64 on a float dataset used to return the raw
+    // IEEE bit patterns (1.5 read as i64 was 4609434218613702656).
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    let path = dir.path().join("float_to_int.h5");
+    let script = format!(
+        r#"{PRELUDE}
+vals = [1.5, -2.75, 3e9, 1e300, -1e300, -0.5, 0.0, 7.99, np.inf, -np.inf, 1e19, -1e19]
+with h5py.File("{path}", "w") as f:
+    for name, dt in (("f8", "<f8"), ("f8be", ">f8"), ("f4", "<f4")):
+        f.create_dataset(name, data=np.array(vals).astype(dt))
+    # libhdf5's half conversions are not saturating (an infinite half becomes
+    # INT_MIN whatever its sign, a negative one wraps as u64), so the half
+    # case stays finite and its u64 read is checked separately below.
+    f.create_dataset("f2", data=np.array([1.5, -2.75, -0.5, 0.0, 7.99, 65504, -65504], "<f2"))
+with h5py.File("{path}", "r") as f:
+    for name in ("f8", "f8be", "f4", "f2"):
+        d = f[name]
+        emit(name + ":i32", d.astype("<i4")[()])
+        emit(name + ":i64", d.astype("<i8")[()])
+        emit(name + ":u64", d.astype("<u8")[()])
+"#,
+        path = path.display()
+    );
+    let expected = run_python(&script);
+
+    let file = File::open(&path).unwrap();
+    for name in ["f8", "f8be", "f4", "f2"] {
+        let ds = file.dataset(name).unwrap();
+        assert_eq!(
+            ds.read_i32().unwrap(),
+            parse::<i32>(&expected[&format!("{name}:i32")]),
+            "{name} as i32"
+        );
+        assert_eq!(
+            ds.read_i64().unwrap(),
+            parse::<i64>(&expected[&format!("{name}:i64")]),
+            "{name} as i64"
+        );
+        if name != "f2" {
+            assert_eq!(
+                ds.read_u64().unwrap(),
+                parse::<u64>(&expected[&format!("{name}:u64")]),
+                "{name} as u64"
+            );
+        }
+    }
+    // Negative values saturate at 0 rather than wrapping.
+    let f2 = file.dataset("f2").unwrap();
+    assert_eq!(f2.read_u64().unwrap(), vec![1, 0, 0, 0, 7, 65504, 0]);
+}