From 44d310ba858090ecea794a834369a191a1add9b9 Mon Sep 17 00:00:00 2001
From: Joseph Hamman <joe@earthmover.io>
Date: Thu, 19 Sep 2024 19:27:27 -0700
Subject: [PATCH] check that fill value is valid for dtype

---
 src/zarr/core/metadata/v3.py      | 12 +++++++++++-
 tests/v3/test_metadata/test_v3.py | 18 ++++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/src/zarr/core/metadata/v3.py b/src/zarr/core/metadata/v3.py
index 6d7253196..34a33103c 100644
--- a/src/zarr/core/metadata/v3.py
+++ b/src/zarr/core/metadata/v3.py
@@ -332,7 +332,17 @@ def parse_fill_value(
                 raise ValueError(msg)
         msg = f"Cannot parse non-string sequence {fill_value} as a scalar with type {dtype}."
         raise TypeError(msg)
-    return dtype.type(fill_value)  # type: ignore[arg-type]
+
+    # Cast the fill_value to the given dtype
+    try:
+        casted_value = np.dtype(dtype).type(fill_value)
+    except (ValueError, OverflowError, TypeError) as e:
+        raise ValueError(f"fill value {fill_value!r} is not valid for dtype {dtype}") from e
+    # Check if the value is still representable by the dtype
+    if fill_value != casted_value:
+        raise ValueError(f"fill value {fill_value!r} is not valid for dtype {dtype}")
+
+    return casted_value
 
 
 # For type checking
diff --git a/tests/v3/test_metadata/test_v3.py b/tests/v3/test_metadata/test_v3.py
index a8f61f90e..7bfa2e019 100644
--- a/tests/v3/test_metadata/test_v3.py
+++ b/tests/v3/test_metadata/test_v3.py
@@ -277,3 +277,21 @@ async def test_invalid_dtype_raises() -> None:
 def test_parse_invalid_dtype_raises(data):
     with pytest.raises(ValueError, match=r"Invalid V3 data_type"):
         parse_dtype(data)
+
+
+@pytest.mark.parametrize(
+    "data_type,fill_value", [("uint8", -1), ("int32", 22.5), ("float32", "foo")]
+)
+async def test_invalid_fill_value_raises(data_type: str, fill_value: int | float) -> None:
+    metadata_dict = {
+        "zarr_format": 3,
+        "node_type": "array",
+        "shape": (1,),
+        "chunk_grid": {"name": "regular", "configuration": {"chunk_shape": (1,)}},
+        "data_type": data_type,
+        "chunk_key_encoding": {"name": "default", "separator": "."},
+        "codecs": (),
+        "fill_value": fill_value,  # this is not a valid fill value for uint8
+    }
+    with pytest.raises(ValueError, match=rf"fill value .* is not valid for dtype {data_type}"):
+        ArrayV3Metadata.from_dict(metadata_dict)