refactor!: rename binary data type to bytes (#118)

closes #114

CHANGELOG.md

@@ -18,6 +18,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Breaking**: Make `{Array,Bytes}PartialDecoderCache` private
 - **Breaking**: Make `Any` a supertrait of partial encoder/decoder traits
 - **Breaking**: Add `ArrayError::UnsupportedMethod`
+- **Breaking**: Rename `DataType::Binary` to `Bytes` for compatibility with `zarr-python`
+- **Breaking**: Make `array::codec::array_to_bytes::bytes::reverse_endianness` private
 
 ### Fixed
 - Cleanup unnecessary lifetime constraints in partial decoders

Cargo.toml

@@ -27,7 +27,7 @@ missing_panics_doc = "warn"
 missing_errors_doc = "warn"
 
 [workspace.dependencies.zarrs_metadata]
-version = "0.2.0"
+version = "0.3.0-dev"
 path = "zarrs_metadata"
 
 [workspace.dependencies.zarrs_storage]

zarrs/doc/status/data_types.md

@@ -4,7 +4,7 @@
 [r* (raw bits)] | [ZEP0001] | ✓ | | |
 | [bfloat16] | [zarr-specs #130] | ✓ | | |
 | [string] (experimental) | [ZEP0007 (draft)] | ✓ | | |
-| [binary] (experimental) | [ZEP0007 (draft)] | ✓ | | |
+| [bytes] (experimental) | [ZEP0007 (draft)] | ✓ | | |
 
 <sup>† Experimental data types are recommended for evaluation only.</sup>
 
@@ -25,7 +25,7 @@
 [bfloat16]: crate::array::data_type::DataType::BFloat16
 [r* (raw bits)]: crate::array::data_type::DataType::RawBits
 [string]: crate::array::data_type::DataType::String
-[binary]: crate::array::data_type::DataType::Binary
+[bytes]: crate::array::data_type::DataType::Bytes
 
 [ZEP0001]: https://zarr.dev/zeps/accepted/ZEP0001.html
 [zarr-specs #130]: https://github.com/zarr-developers/zarr-specs/issues/130

zarrs/src/array/codec/array_to_bytes/bytes.rs

@@ -47,7 +47,7 @@ pub(crate) fn create_codec_bytes(metadata: &MetadataV3) -> Result<Codec, PluginC
 }
 
 /// Reverse the endianness of bytes for a given data type.
-pub fn reverse_endianness(v: &mut [u8], data_type: &DataType) {
+pub(crate) fn reverse_endianness(v: &mut [u8], data_type: &DataType) {
     match data_type {
         DataType::Bool | DataType::Int8 | DataType::UInt8 | DataType::RawBits(_) => {}
         DataType::Int16 | DataType::UInt16 | DataType::Float16 | DataType::BFloat16 => {
@@ -72,7 +72,7 @@ pub fn reverse_endianness(v: &mut [u8], data_type: &DataType) {
             v.chunks_exact_mut(8).for_each(swap);
         }
         // Variable-sized data types are not supported and are rejected outside of this function
-        DataType::String | DataType::Binary => unreachable!(),
+        DataType::String | DataType::Bytes => unreachable!(),
     }
 }
 

zarrs/src/array/data_type.rs

@@ -56,7 +56,7 @@ pub enum DataType {
     /// A UTF-8 encoded string.
     String,
     /// Variable-sized binary data.
-    Binary,
+    Bytes,
 }
 
 /// An unsupported data type error.
@@ -104,7 +104,7 @@ impl DataType {
             Self::Complex128 => "complex128",
             Self::RawBits(_usize) => "r*",
             Self::String => "string",
-            Self::Binary => "binary",
+            Self::Bytes => "bytes",
             // Self::Extension(extension) => extension.identifier(),
         }
     }
@@ -140,7 +140,7 @@ impl DataType {
             Self::Complex128 => DataTypeMetadataV3::Complex128,
             Self::RawBits(size) => DataTypeMetadataV3::RawBits(*size),
             Self::String => DataTypeMetadataV3::String,
-            Self::Binary => DataTypeMetadataV3::Binary,
+            Self::Bytes => DataTypeMetadataV3::Bytes,
         }
     }
 
@@ -154,7 +154,7 @@ impl DataType {
             Self::Int64 | Self::UInt64 | Self::Float64 | Self::Complex64 => DataTypeSize::Fixed(8),
             Self::Complex128 => DataTypeSize::Fixed(16),
             Self::RawBits(size) => DataTypeSize::Fixed(*size),
-            Self::String | Self::Binary => DataTypeSize::Variable,
+            Self::String | Self::Bytes => DataTypeSize::Variable,
             // Self::Extension(extension) => extension.size(),
         }
     }
@@ -192,7 +192,7 @@ impl DataType {
             DataTypeMetadataV3::Complex128 => Ok(Self::Complex128),
             DataTypeMetadataV3::RawBits(size) => Ok(Self::RawBits(*size)),
             DataTypeMetadataV3::String => Ok(Self::String),
-            DataTypeMetadataV3::Binary => Ok(Self::Binary),
+            DataTypeMetadataV3::Bytes => Ok(Self::Bytes),
             DataTypeMetadataV3::Unknown(metadata) => {
                 Err(UnsupportedDataTypeError(metadata.to_string()))
             }
@@ -241,7 +241,7 @@ impl DataType {
                 }
                 Err(err())
             }
-            Self::Binary => {
+            Self::Bytes => {
                 if let FillValueMetadataV3::ByteArray(bytes) = fill_value {
                     Ok(FillValue::new(bytes.clone()))
                 } else {
@@ -329,7 +329,7 @@ impl DataType {
             Self::String => FillValueMetadataV3::String(
                 String::from_utf8(fill_value.as_ne_bytes().to_vec()).unwrap(),
             ),
-            Self::Binary => FillValueMetadataV3::ByteArray(fill_value.as_ne_bytes().to_vec()),
+            Self::Bytes => FillValueMetadataV3::ByteArray(fill_value.as_ne_bytes().to_vec()),
         }
     }
 }

zarrs/src/array/element.rs

@@ -221,7 +221,7 @@ macro_rules! impl_element_binary {
     ($raw_type:ty) => {
         impl Element for $raw_type {
             fn validate_data_type(data_type: &DataType) -> Result<(), ArrayError> {
-                (data_type == &DataType::Binary).then_some(()).ok_or(IET)
+                (data_type == &DataType::Bytes).then_some(()).ok_or(IET)
             }
 
             fn into_array_bytes<'a>(

zarrs/tests/array_sync.rs

@@ -324,7 +324,7 @@ fn array_binary() -> Result<(), Box<dyn std::error::Error>> {
     let array_path = "/array";
     let mut builder = ArrayBuilder::new(
         vec![4, 4], // array shape
-        DataType::Binary,
+        DataType::Bytes,
         vec![2, 2].try_into().unwrap(), // regular chunk shape
         FillValue::from([]),
     );

zarrs_metadata/CHANGELOG.md

@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+- **Breaking**: Rename `DataTypeMetadataV3::Binary` to `Bytes` for compatibility with `zarr-python`
+
 ## [0.2.0] - 2024-11-15
 
 ### Added

zarrs_metadata/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "zarrs_metadata"
-version = "0.2.0"
+version = "0.3.0-dev"
 authors = ["Lachlan Deakin <[email protected]>"]
 edition = "2021"
 rust-version = "1.77"

zarrs_metadata/src/v3/array/data_type.rs

@@ -46,7 +46,7 @@ pub enum DataTypeMetadataV3 {
     /// A UTF-8 encoded string.
     String,
     /// Variable-sized binary data.
-    Binary,
+    Bytes,
     /// An unknown data type.
     Unknown(MetadataV3),
 }
@@ -105,7 +105,7 @@ impl DataTypeMetadataV3 {
             Self::Complex64 => "complex64".to_string(),
             Self::Complex128 => "complex128".to_string(),
             Self::String => "string".to_string(),
-            Self::Binary => "binary".to_string(),
+            Self::Bytes => "bytes".to_string(),
             Self::RawBits(size) => format!("r{}", size * 8),
             Self::Unknown(metadata) => metadata.name().to_string(),
         }
@@ -134,7 +134,7 @@ impl DataTypeMetadataV3 {
             }
             Self::Complex128 => Some(DataTypeSize::Fixed(16)),
             Self::RawBits(size) => Some(DataTypeSize::Fixed(*size)),
-            Self::String | Self::Binary => Some(DataTypeSize::Variable),
+            Self::String | Self::Bytes => Some(DataTypeSize::Variable),
             Self::Unknown(_) => None,
         }
     }
@@ -170,7 +170,7 @@ impl DataTypeMetadataV3 {
             "complex64" => return Self::Complex64,
             "complex128" => return Self::Complex128,
             "string" => return Self::String,
-            "binary" => return Self::Binary,
+            "bytes" => return Self::Bytes,
             _ => {}
         };