Merge branch 'fix/p0-writer-meta' into fix/phase0-correctness

crates/clawhdf5/src/reader.rs

@@ -478,7 +478,12 @@ impl<'f> Dataset<'f> {
         // sparse) dataset — select from a fill-aware full read instead. (The
         // selection reader currently decodes the full dataset too, so this
         // costs nothing extra.)
-        let fill = clawhdf5_format::fill_value::dataset_fill_value(&self.header.messages)?;
+        let fill = clawhdf5_format::fill_value::dataset_fill_value_in(
+            self.file.data.as_bytes(),
+            &self.header.messages,
+            self.file.offset_size(),
+            self.file.length_size(),
+        )?;
         let fill_matters = !clawhdf5_format::fill_value::has_storage(&dl)
             || (matches!(dl, DataLayout::Chunked { .. })
                 && !clawhdf5_format::fill_value::is_default(fill.as_deref()));

crates/clawhdf5/tests/shared_fill_value.rs

@@ -0,0 +1,49 @@
+//! Datasets whose Fill Value message is shared through the file's SOHM heap
+//! (fixture written by HDF5 2.0, see `gen_shared_fill.py`). Their unwritten
+//! storage must read as the fill value (-7), not as zeros.
+
+use clawhdf5::File;
+use clawhdf5_format::selection::Selection;
+
+const FIXTURE: &[u8] = include_bytes!("../../clawhdf5-format/tests/fixtures/shared_fill_value.h5");
+
+#[test]
+fn shared_fill_value_applies_to_unwritten_storage() {
+    let file = File::from_bytes(FIXTURE.to_vec()).unwrap();
+    // `_a` keeps its fill value in its own header, `_b` references the SOHM
+    // heap; both must read the same.
+    for name in ["sohm_a", "sohm_b"] {
+        assert_eq!(
+            file.dataset(name).unwrap().read_i32().unwrap(),
+            [0, 1, 2, 3, -7, -7, -7, -7],
+            "{name}"
+        );
+    }
+    for name in ["unwritten_a", "unwritten_b"] {
+        assert_eq!(
+            file.dataset(name).unwrap().read_i32().unwrap(),
+            [-7, -7, -7],
+            "{name}"
+        );
+    }
+
+    // The selection path decides on its own whether the fill value matters.
+    let slab = Selection::Hyperslab {
+        start: vec![2],
+        stride: vec![1],
+        count: vec![4],
+        block: vec![1],
+    };
+    let raw = file
+        .dataset("sohm_b")
+        .unwrap()
+        .read_selection(&slab)
+        .unwrap();
+    let values: Vec<i32> = raw
+        .as_chunks::<4>()
+        .0
+        .iter()
+        .map(|b| i32::from_le_bytes(*b))
+        .collect();
+    assert_eq!(values, [2, 3, -7, -7]);
+}