fix(tools): h5rs dump shows NUL padding in nested strings, like h5dump

A null-padded fixed string inside a compound or an array member printed trimmed ("" for three NULs, "a" for "a\0b"), where h5dump prints every byte ("\000\000\000", "a\000b"); only top-level strings were shown in full. DATA blocks now render elements through one function that keeps the padding at any depth. The README now lists the remaining known differences from h5dump: nested compounds print inline, and long double values are printed as errors (exit 1) with the datatype as an H5T_FLOAT block. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 01:23:32 -05:00
parent b8492bd28d
commit c4d96c1390
5 changed files with 124 additions and 21 deletions
@@ -72,10 +72,22 @@ groups; integers of both byte orders, floats, compound with an array member,
 enum, fixed and variable-length strings; soft, external and hard links; a
 named datatype; compact and dense attributes) `h5rs dump` and `h5rs dump -A`
 print the same bytes as h5dump 1.14.6 — `dump_matches_h5dump` in
-`tests/h5rs_interop.rs` checks this. Not covered by that test: references,
-opaque, bitfield, variable-length sequences and virtual datasets. Floats print at their own precision (a `float32` 0.1 prints as
-`0.1`), which for some values is more digits than h5dump's `%g`. The `-p`
-block is h5rs's own (it names the chunk index), not h5dump's.
+`tests/h5rs_interop.rs` checks this, and `dump_shows_nul_padding_in_nested_strings`
+that null-padded strings show their NULs (`"a\000b"`) at any depth, as
+h5dump's do. Not covered by those tests: references, opaque, bitfield,
+variable-length sequences and virtual datasets. Known differences from
+h5dump:
+
+- Floats print at their own precision (a `float32` 0.1 prints as `0.1`),
+  which for some values is more digits than h5dump's `%g`.
+- A compound nested in a compound prints inline (`{ 1, 2.5 }`) where
+  h5dump prints it as an indented block, one member per line; only the
+  outer compound is a block.
+- `long double` (x87 80-bit) and other floats wider than 64 bits: the
+  datatype is printed as an `H5T_FLOAT { ... }` block instead of h5dump's
+  one-line description, and each value as `<error: ...>`; `dump` then
+  exits 1. The library cannot convert them (see `docs/known-issues.md`).
+- The `-p` block is h5rs's own (it names the chunk index), not h5dump's.

 ### JSON schema

@@ -518,7 +518,9 @@ impl Dump<'_> {
                errors += 1;
            }
            let comma = if i + 1 < n { "," } else { "" };
-            if let Value::Compound(members) = &v {
+            let esize = dt.type_size() as usize;
+            let eb = raw.get(i * esize..(i + 1) * esize).unwrap_or_default();
+            if let (Value::Compound(_), Datatype::Compound { members, .. }) = (&v, dt) {
                // h5dump prints each compound element as a block, one
                // member per line.
                if !line.is_empty() {
@@ -526,25 +528,22 @@ impl Dump<'_> {
                    line.clear();
                }
                writeln!(out.o, "{pad}({}): {{", index_text(i as u64, &dims))?;
-                for (k, (_, m)) in members.iter().enumerate() {
+                for (k, m) in members.iter().enumerate() {
                    let sep = if k + 1 < members.len() { "," } else { "" };
-                    writeln!(out.o, "{pad}      {}{sep}", value::text(m, &paths))?;
+                    let mb = usize::try_from(m.byte_offset)
+                        .ok()
+                        .and_then(|o| eb.get(o..))
+                        .unwrap_or_default();
+                    let t = ddl_text(&dec, &m.datatype, mb, &paths, 1);
+                    writeln!(out.o, "{pad}      {t}{sep}")?;
                }
                writeln!(out.o, "{pad}   }}{comma}")?;
                continue;
            }
-            let t = match dt {
-                // h5dump shows a null-padded string's padding.
-                Datatype::String {
-                    padding: StringPadding::NullPad,
-                    size,
-                    ..
-                } if !matches!(v, Value::Error(_)) => {
-                    let sz = *size as usize;
-                    let b = raw.get(i * sz..(i + 1) * sz).unwrap_or_default();
-                    format!("{}{comma}", value::quote_bytes(b))
-                }
-                _ => format!("{}{comma}", value::text(&v, &paths)),
+            let t = if matches!(v, Value::Error(_)) {
+                format!("{}{comma}", value::text(&v, &paths))
+            } else {
+                format!("{}{comma}", ddl_text(&dec, dt, eb, &paths, 0))
            };
            let row_start = i % last == 0;
            if row_start || line.len() + 1 + t.len() > 77 {
@@ -863,6 +862,65 @@ const MAX_DDL_DEPTH: usize = 256;
 const JSON_BYTES_PER_ELEMENT: u64 = 64;

 /// `(i,j,k)` index of flat element `i` of an array with `dims`.
+/// One element as h5dump prints it in a DATA block: [`value::text`], except
+/// that a null-padded fixed string shows its padding (every byte, NULs as
+/// `\000`) at any depth, in compound members and array elements too.
+fn ddl_text(
+    dec: &Decoder,
+    dt: &Datatype,
+    b: &[u8],
+    paths: &dyn Fn(u64) -> Option<String>,
+    depth: u32,
+) -> String {
+    let err = || value::text(&Value::Error("short element".into()), paths);
+    if depth > 32 {
+        return value::text(&dec.decode(dt, b, depth), paths);
+    }
+    match dt {
+        Datatype::String {
+            padding: StringPadding::NullPad,
+            size,
+            ..
+        } => match b.get(..*size as usize) {
+            Some(s) => value::quote_bytes(s),
+            None => err(),
+        },
+        Datatype::Compound { members, .. } => format!(
+            "{{ {} }}",
+            members
+                .iter()
+                .map(
+                    |m| match usize::try_from(m.byte_offset).ok().and_then(|o| b.get(o..)) {
+                        Some(mb) => ddl_text(dec, &m.datatype, mb, paths, depth + 1),
+                        None => err(),
+                    }
+                )
+                .collect::<Vec<_>>()
+                .join(", ")
+        ),
+        Datatype::Array {
+            base_type,
+            dimensions,
+        } => {
+            let bs = base_type.type_size() as usize;
+            let n = dimensions
+                .iter()
+                .try_fold(1usize, |a, &d| a.checked_mul(d as usize));
+            match n.filter(|n| n.checked_mul(bs).is_some_and(|t| t <= b.len())) {
+                Some(n) => format!(
+                    "[ {} ]",
+                    (0..n)
+                        .map(|k| ddl_text(dec, base_type, &b[k * bs..], paths, depth + 1))
+                        .collect::<Vec<_>>()
+                        .join(", ")
+                ),
+                None => value::text(&dec.decode(dt, b, depth), paths),
+            }
+        }
+        _ => value::text(&dec.decode(dt, b, depth), paths),
+    }
+}
+
 fn index_text(mut i: u64, dims: &[u64]) -> String {
    let mut idx = vec![0u64; dims.len()];
    for (k, &d) in dims.iter().enumerate().rev() {
@@ -149,6 +149,15 @@ for name, t in (("target1.h5", "/a"), ("target2.h5", "/b")):
        f["s"] = h5py.SoftLink(t)
        f["rel"] = h5py.SoftLink("a")

+# Null-padded fixed strings with NULs, at the top level and nested in a
+# compound and in an array member.
+with h5py.File(os.path.join(out, "nulstrings.h5"), "w") as f:
+    f["top"] = np.array([b"", b"ab", b"a\x00b"], dtype="S3")
+    f["cmp"] = np.array(
+        [(b"", 1), (b"ab", 2), (b"a\x00b", 3)], dtype=[("s", "S3"), ("i", "i4")]
+    )
+    f["arr"] = np.array([([b"", b"x"],)], dtype=[("v", "(2,)S2")])
+
 with h5py.File(os.path.join(out, "userblock.h5"), "w", userblock_size=1024) as f:
    f["d"] = np.arange(10)

@@ -280,6 +280,28 @@ fn dump_matches_h5dump() {
    );
 }

+/// A null-padded fixed string prints every byte (NULs as `\000`), as
+/// h5dump prints it, also inside a compound and an array member.
+#[test]
+fn dump_shows_nul_padding_in_nested_strings() {
+    let Some(f) = generate() else { return };
+    let p = f.p("nulstrings.h5");
+    let ours = stdout(&h5rs(&["dump", &p]));
+    for want in [
+        r#"(0): "\000\000\000", "ab\000", "a\000b""#,
+        r#""\000\000\000","#,
+        r#""a\000b","#,
+        r#"[ "\000\000", "x\000" ]"#,
+    ] {
+        assert!(ours.contains(want), "no {want} in\n{ours}");
+    }
+    if missing(tool_available("h5dump"), "h5dump") {
+        return;
+    }
+    let reference = run("h5dump", &[&p]);
+    assert_eq!(ours, stdout(&reference).replacen(&p, "nulstrings.h5", 1));
+}
+
 #[test]
 fn dump_json_values_match_h5py() {
    let Some(f) = generate() else { return };