datachain 0.19__tar.gz → 0.19.1__tar.gz

{datachain-0.19 → datachain-0.19.1}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.11.12'
+    rev: 'v0.11.13'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.19 → datachain-0.19.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.19
+Version: 0.19.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.19 → datachain-0.19.1}/src/datachain/lib/arrow.py

@@ -241,6 +241,8 @@ def arrow_type_mapper(col_type: pa.DataType, column: str = "") -> type:  # noqa:
         return dict
     if isinstance(col_type, pa.lib.DictionaryType):
         return arrow_type_mapper(col_type.value_type)  # type: ignore[return-value]
+    if pa.types.is_null(col_type):
+        return str  # use strings for null columns
     raise TypeError(f"{col_type!r} datatypes not supported, column: {column}")
 
 

{datachain-0.19 → datachain-0.19.1}/src/datachain.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.19
+Version: 0.19.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.19 → datachain-0.19.1}/tests/unit/lib/test_arrow.py

@@ -154,6 +154,7 @@ def test_arrow_generator_partitioned(tmp_path, catalog, cache):
         (pa.map_(pa.string(), pa.int32()), dict),
         (pa.dictionary(pa.int64(), pa.string()), str),
         (pa.list_(pa.string()), list[str]),
+        (pa.null(), str),
     ),
 )
 def test_arrow_type_mapper(col_type, expected):
@@ -161,11 +162,11 @@ def test_arrow_type_mapper(col_type, expected):
 
 
 def test_arrow_type_mapper_struct():
-    col_type = pa.struct({"x": pa.int32(), "y": pa.string()})
+    col_type = pa.struct({"x": pa.int32(), "y": pa.string(), "z": pa.null()})
     fields = arrow_type_mapper(col_type).model_fields
-    assert list(fields.keys()) == ["x", "y"]
+    assert list(fields.keys()) == ["x", "y", "z"]
     dtypes = [field.annotation for field in fields.values()]
-    assert dtypes == [Optional[int], Optional[str]]
+    assert dtypes == [Optional[int], Optional[str], Optional[str]]
 
 
 def test_arrow_type_error():