Merge branch 'main' into codec_metadata_v2_to_v3

zarrs/tests/data/v2_str0.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env -S uv run
+# /// script
+# requires-python = ">=3.12"
+# dependencies = [
+#     "zarr==3.0.1",
+# ]
+# ///
+
+import zarr
+
+path_out = "tests/data/zarr_python_compat/str_v2_fv_0.zarr"
+array = zarr.create_array(
+    path_out,
+    dtype=str,
+    shape=(5,),
+    chunks=(2,),
+    filters=zarr.codecs.vlen_utf8.VLenUTF8(),
+    compressors=[None],
+    fill_value=0,
+    zarr_format=2,
+    overwrite=True,
+)
+array[:3] = ["a", "bb", ""]
+print(array.info)
+# assert (array[:] == ["a", "bb", "", "", ""]).all() # FAILURE
+
+path_out = "tests/data/zarr_python_compat/str_v2_fv_null.zarr"
+array = zarr.create_array(
+    path_out,
+    dtype=str,
+    shape=(5,),
+    chunks=(2,),
+    filters=zarr.codecs.vlen_utf8.VLenUTF8(),
+    compressors=[None],
+    fill_value=None,
+    zarr_format=2,
+    overwrite=True,
+)
+array[:3] = ["a", "bb", ""]
+print(array.info)
+print(array[:])
+assert (array[:] == ["a", "bb", "", "", ""]).all()

zarrs/tests/data/zarr_python_compat/str_v2_fv_0.zarr/.zarray

@@ -0,0 +1,19 @@
+{
+  "shape": [
+    5
+  ],
+  "chunks": [
+    2
+  ],
+  "fill_value": 0,
+  "order": "C",
+  "filters": [
+    {
+      "id": "vlen-utf8"
+    }
+  ],
+  "dimension_separator": ".",
+  "compressor": null,
+  "zarr_format": 2,
+  "dtype": "|O"
+}

zarrs/tests/data/zarr_python_compat/str_v2_fv_0.zarr/.zattrs

@@ -0,0 +1 @@
+{}

zarrs/tests/data/zarr_python_compat/str_v2_fv_null.zarr/.zarray

@@ -0,0 +1,19 @@
+{
+  "shape": [
+    5
+  ],
+  "chunks": [
+    2
+  ],
+  "fill_value": null,
+  "order": "C",
+  "filters": [
+    {
+      "id": "vlen-utf8"
+    }
+  ],
+  "dimension_separator": ".",
+  "compressor": null,
+  "zarr_format": 2,
+  "dtype": "|O"
+}

zarrs/tests/data/zarr_python_compat/str_v2_fv_null.zarr/.zattrs

@@ -0,0 +1 @@
+{}

zarrs/tests/zarr_python_compat.rs

@@ -43,3 +43,31 @@ fn zarr_python_compat_fletcher32_v2() -> Result<(), Box<dyn Error>> {
 
     Ok(())
 }
+
+#[test]
+fn zarr_python_v2_compat_str_fv_0() -> Result<(), Box<dyn Error>> {
+    let store = Arc::new(FilesystemStore::new(
+        "tests/data/zarr_python_compat/str_v2_fv_0.zarr",
+    )?);
+    let array = zarrs::array::Array::open(store.clone(), "/")?;
+    let subset_all = array.subset_all();
+    let elements = array.retrieve_array_subset_elements::<String>(&subset_all)?;
+
+    assert_eq!(elements, &["a", "bb", "", "", ""]);
+
+    Ok(())
+}
+
+#[test]
+fn zarr_python_v2_compat_str_fv_null() -> Result<(), Box<dyn Error>> {
+    let store = Arc::new(FilesystemStore::new(
+        "tests/data/zarr_python_compat/str_v2_fv_null.zarr",
+    )?);
+    let array = zarrs::array::Array::open(store.clone(), "/")?;
+    let subset_all = array.subset_all();
+    let elements = array.retrieve_array_subset_elements::<String>(&subset_all)?;
+
+    assert_eq!(elements, &["a", "bb", "", "", ""]);
+
+    Ok(())
+}

zarrs_metadata/CHANGELOG.md

@@ -11,6 +11,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Derive `Copy` for `ArrayMetadataV2Order`
 - Add `codec_metadata_v2_to_v3`
 
+### Fixed
+- Interpret a `0` fill value as `""` for Zarr V2 string arrays (for `zarr-python` compatibility) ([#140] by [@zqfang])
+
+[#140]: https://github.com/LDeakin/zarrs/pull/140
+
 ## [0.3.1] - 2025-01-29
 
 ### Fixed
@@ -70,3 +75,5 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.3.0]: https://github.com/LDeakin/zarrs/releases/tag/zarrs_metadata-v0.3.0
 [0.2.0]: https://github.com/LDeakin/zarrs/releases/tag/zarrs_metadata-v0.2.0
 [0.1.0]: https://github.com/LDeakin/zarrs/releases/tag/zarrs_metadata-v0.1.0
+
+[@zqfang]: https://github.com/zqfang

zarrs_metadata/src/v2_to_v3.rs

@@ -253,6 +253,11 @@ pub fn array_metadata_v2_to_v3(
                 ));
             }
         }
+    } else if data_type.name() == "string" {
+        // Add a special case for `zarr-python` string data with a 0 fill value -> empty string
+        if let Some(0) = fill_value.try_as_uint::<u64>() {
+            fill_value = FillValueMetadataV3::String(String::new());
+        }
     }
 
     let codecs = codec_metadata_v2_to_v3(