Merge branch 'main' into compliant-group-by

Author: dangotbanned

docs/api-reference/dtypes.md

@@ -36,6 +36,7 @@
         - Unknown
         - UnsignedIntegerType
         - Time
+        - Binary
       show_root_heading: false
       show_source: false
       show_bases: false

narwhals/__init__.py

@@ -8,6 +8,7 @@
 from narwhals.dataframe import DataFrame
 from narwhals.dataframe import LazyFrame
 from narwhals.dtypes import Array
+from narwhals.dtypes import Binary
 from narwhals.dtypes import Boolean
 from narwhals.dtypes import Categorical
 from narwhals.dtypes import Date
@@ -85,6 +86,7 @@
 
 __all__ = [
     "Array",
+    "Binary",
     "Boolean",
     "Categorical",
     "DataFrame",

narwhals/_arrow/utils.py

@@ -156,6 +156,8 @@ def native_to_narwhals_dtype(dtype: pa.DataType, version: Version) -> DType:
         return dtypes.Decimal()
     if pa.types.is_time32(dtype) or pa.types.is_time64(dtype):
         return dtypes.Time()
+    if pa.types.is_binary(dtype):
+        return dtypes.Binary()
     return dtypes.Unknown()  # pragma: no cover
 
 
@@ -211,6 +213,8 @@ def narwhals_to_native_dtype(dtype: DType | type[DType], version: Version) -> pa
         return pa.list_(inner, list_size=list_size)
     if isinstance_or_issubclass(dtype, dtypes.Time):
         return pa.time64("ns")
+    if isinstance_or_issubclass(dtype, dtypes.Binary):
+        return pa.binary()
 
     msg = f"Unknown dtype: {dtype}"  # pragma: no cover
     raise AssertionError(msg)

narwhals/_dask/utils.py

@@ -147,6 +147,9 @@ def narwhals_to_native_dtype(dtype: DType | type[DType], version: Version) -> An
     if isinstance_or_issubclass(dtype, dtypes.Time):  # pragma: no cover
         msg = "Converting to Time dtype is not supported yet"
         return NotImplementedError(msg)
+    if isinstance_or_issubclass(dtype, dtypes.Binary):  # pragma: no cover
+        msg = "Converting to Binary dtype is not supported yet"
+        return NotImplementedError(msg)
 
     msg = f"Unknown dtype: {dtype}"  # pragma: no cover
     raise AssertionError(msg)

narwhals/_duckdb/utils.py

@@ -116,6 +116,8 @@ def native_to_narwhals_dtype(duckdb_dtype: str, version: Version) -> DType:
         return dtypes.Decimal()
     if duckdb_dtype == "TIME":
         return dtypes.Time()
+    if duckdb_dtype == "BLOB":
+        return dtypes.Binary()
     return dtypes.Unknown()  # pragma: no cover
 
 
@@ -154,6 +156,8 @@ def narwhals_to_native_dtype(dtype: DType | type[DType], version: Version) -> st
         return "BOOLEAN"
     if isinstance_or_issubclass(dtype, dtypes.Time):
         return "TIME"
+    if isinstance_or_issubclass(dtype, dtypes.Binary):
+        return "BLOB"
     if isinstance_or_issubclass(dtype, dtypes.Categorical):
         msg = "Categorical not supported by DuckDB"
         raise NotImplementedError(msg)

narwhals/_ibis/dataframe.py

@@ -71,6 +71,8 @@ def native_to_narwhals_dtype(ibis_dtype: Any, version: Version) -> DType:
         return dtypes.Decimal()
     if ibis_dtype.is_time():
         return dtypes.Time()
+    if ibis_dtype.is_binary():
+        return dtypes.Binary()
     return dtypes.Unknown()  # pragma: no cover
 
 

narwhals/_pandas_like/utils.py

@@ -394,6 +394,8 @@ def non_object_native_to_narwhals_dtype(dtype: str, version: Version) -> DType:
         return dtypes.Decimal()
     if dtype.startswith("time") and dtype.endswith("[pyarrow]"):
         return dtypes.Time()
+    if dtype.startswith("binary") and dtype.endswith("[pyarrow]"):
+        return dtypes.Binary()
     return dtypes.Unknown()  # pragma: no cover
 
 
@@ -593,7 +595,7 @@ def narwhals_to_native_dtype(  # noqa: PLR0915
         msg = "Converting to Enum is not (yet) supported"
         raise NotImplementedError(msg)
     if isinstance_or_issubclass(
-        dtype, (dtypes.Struct, dtypes.Array, dtypes.List, dtypes.Time)
+        dtype, (dtypes.Struct, dtypes.Array, dtypes.List, dtypes.Time, dtypes.Binary)
     ):
         if implementation is Implementation.PANDAS and backend_version >= (2, 2):
             try:

narwhals/_polars/utils.py

@@ -147,6 +147,8 @@ def native_to_narwhals_dtype(
         return dtypes.Decimal()
     if dtype == pl.Time:
         return dtypes.Time()
+    if dtype == pl.Binary:
+        return dtypes.Binary()
     return dtypes.Unknown()
 
 
@@ -192,6 +194,8 @@ def narwhals_to_native_dtype(
         return pl.Date()
     if dtype == dtypes.Time:
         return pl.Time()
+    if dtype == dtypes.Binary:
+        return pl.Binary()
     if dtype == dtypes.Decimal:
         msg = "Casting to Decimal is not supported yet."
         raise NotImplementedError(msg)

narwhals/_spark_like/utils.py

@@ -79,6 +79,8 @@ def native_to_narwhals_dtype(
                 for field in dtype
             ]
         )
+    if isinstance(dtype, native.BinaryType):
+        return dtypes.Binary()
     return dtypes.Unknown()
 
 
@@ -135,6 +137,8 @@ def narwhals_to_native_dtype(
                 for field in dtype.fields
             ]
         )
+    if isinstance_or_issubclass(dtype, dtypes.Binary):
+        return native.BinaryType()
 
     if isinstance_or_issubclass(
         dtype,

narwhals/dtypes.py

@@ -696,3 +696,27 @@ class Time(TemporalType):
        >>> nw.from_native(rel).schema["t"]
        Time
     """
+
+
+class Binary(DType):
+    """Binary type.
+
+    Examples:
+        >>> import polars as pl
+        >>> import narwhals as nw
+        >>> import pyarrow as pa
+        >>> import duckdb
+        >>> data = [b"test1", b"test2"]
+        >>> ser_pl = pl.Series(data, dtype=pl.Binary)
+        >>> ser_pa = pa.chunked_array([pa.array(data, type=pa.binary())])
+        >>> rel = duckdb.sql(
+        ...     "SELECT * FROM (VALUES (BLOB 'test1'), (BLOB 'test2')) AS df(t)"
+        ... )
+
+        >>> nw.from_native(ser_pl, series_only=True).dtype
+        Binary
+        >>> nw.from_native(ser_pa, series_only=True).dtype
+        Binary
+        >>> nw.from_native(rel).schema["t"]
+        Binary
+    """