fix(format): flag non-ASCII link names as UTF-8

The writer marked every link name ASCII, so a name such as "größe" was stored as UTF-8 bytes under the ASCII character set (h5py reports cset 0 for it). Names that are not plain ASCII now carry the UTF-8 flag, as h5py writes them; ASCII names are unchanged. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 08:34:04 -05:00
parent d102c06306
commit bd36fe883b
3 changed files with 32 additions and 1 deletions
@@ -592,3 +592,21 @@ fn track_order_lists_members_in_creation_order() {
    assert_eq!(out, r#"["aaa", ["soft", "aaa"], 21]"#);
    h5dump_ok(&path);
 }
+
+#[test]
+fn non_ascii_names_are_utf8() {
+    skip_if_no_python!();
+    let dir = tempfile::tempdir().unwrap();
+    let mut b = FileBuilder::new();
+    b.create_dataset("größe/wert").with_i32_data(&[1]);
+    let path = write(&dir, "utf8.h5", b);
+    let out = h5py(
+        &path,
+        "with h5py.File(path, 'r') as f:\n\
+         \x20   l = f.id.links.get_info('größe'.encode())\n\
+         \x20   print(json.dumps([list(f), list(f['größe']), l.cset], ensure_ascii=False))",
+    );
+    assert_eq!(out, r#"[["größe"], ["wert"], 1]"#);
+    let f = File::open(&path).unwrap();
+    assert_eq!(f.dataset("größe/wert").unwrap().read_i32().unwrap(), [1]);
+}