fix(format): give empty string attributes a 1-byte type

An empty AttrValue::String (or a StringArray of empty strings) was written with a size-0 fixed-length string type. libhdf5 rejects that ("invalid datatype size"), and the failure takes every attribute on the object with it. Strings are now at least 1 byte, NUL-padded, which is how h5py stores "" and reads back as "" in both h5py and our reader. check_encodable also refuses a size-0 string type passed in directly. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-25 21:12:12 -05:00
parent 8c3ef996ea
commit 14876b8ae5
3 changed files with 71 additions and 3 deletions
@@ -464,3 +464,63 @@ fn h5py_sees_our_fill_time_and_fill_value() {
    );
    h5dump_ok(&path);
 }
+
+// ---- 5. empty string attributes ----
+
+fn empty_string_file() -> Vec<u8> {
+    let mut fw = FileWriter::new();
+    fw.set_root_attr("empty", AttrValue::String(String::new()));
+    fw.set_root_attr("x", AttrValue::String("héllo".into()));
+    fw.set_root_attr(
+        "empties",
+        AttrValue::StringArray(vec![String::new(), String::new()]),
+    );
+    fw.set_root_attr("n", AttrValue::I64(3));
+    fw.finish().unwrap()
+}
+
+#[test]
+fn empty_string_attribute_has_a_one_byte_type() {
+    // Measured: "" got a size-0 string type, and libhdf5 then refused every
+    // attribute on the object ("invalid datatype size").
+    let bytes = empty_string_file();
+    let (sb, root) = header_at(&bytes, "/");
+    let attrs = clawhdf5_format::attribute::extract_attributes(&root, sb.length_size).unwrap();
+    for name in ["empty", "empties"] {
+        let a = attrs.iter().find(|a| a.name == name).unwrap();
+        assert_eq!(a.datatype.type_size(), 1, "{name}");
+        let strings = a.read_as_strings().unwrap();
+        assert!(strings.iter().all(String::is_empty), "{name}: {strings:?}");
+    }
+
+    // A size-0 string type handed in directly is refused, not written.
+    let mut fw = FileWriter::new();
+    fw.set_root_attr(
+        "raw",
+        AttrValue::Raw {
+            datatype: Datatype::String {
+                size: 0,
+                padding: clawhdf5_format::datatype::StringPadding::NullPad,
+                charset: clawhdf5_format::datatype::CharacterSet::Ascii,
+            },
+            shape: vec![],
+            data: vec![],
+        },
+    );
+    assert!(fw.finish().is_err());
+}
+
+#[test]
+#[ignore = "requires Python h5py module and h5dump"]
+fn h5py_reads_all_attributes_next_to_an_empty_string() {
+    let path = write_tmp("empty_str", &empty_string_file());
+    let out = h5py(
+        &path,
+        "f = h5py.File(path, 'r')\n\
+         d = lambda v: v.decode() if isinstance(v, bytes) else v\n\
+         print(json.dumps([d(f.attrs['empty']), d(f.attrs['x']),\n\
+         \x20   [d(s) for s in f.attrs['empties']], int(f.attrs['n'])], ensure_ascii=False))",
+    );
+    assert_eq!(out, r#"["", "héllo", ["", ""], 3]"#);
+    h5dump_ok(&path);
+}