dataframely 1.7.0__tar.gz → 1.7.2__tar.gz

{dataframely-1.7.0 → dataframely-1.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.7.0
+Version: 1.7.2
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12

{dataframely-1.7.0 → dataframely-1.7.2}/dataframely/__init__.py

@@ -14,7 +14,7 @@ from . import random
 from ._base_collection import CollectionMember
 from ._filter import filter
 from ._rule import rule
-from ._typing import DataFrame, LazyFrame
+from ._typing import DataFrame, LazyFrame, Validation
 from .collection import Collection, deserialize_collection
 from .columns import (
     Any,
@@ -96,4 +96,5 @@ __all__ = [
     "List",
     "Array",
     "Object",
+    "Validation",
 ]

{dataframely-1.7.0 → dataframely-1.7.2}/dataframely/_extre.pyi

@@ -1,4 +1,4 @@
-from typing import Literal, overload
+from typing import overload
 
 def matching_string_length(regex: str) -> tuple[int, int | None]:
     """
@@ -48,7 +48,7 @@ def sample(
 @overload
 def sample(
     regex: str,
-    n: Literal[None] = None,
+    n: None = None,
     max_repetitions: int = 16,
     seed: int | None = None,
 ) -> str: ...

{dataframely-1.7.0 → dataframely-1.7.2}/dataframely/failure.py

@@ -97,7 +97,7 @@ class FailureInfo(Generic[S]):
             Be aware that this method suffers from the same limitations as
             :meth:`Schema.serialize`.
         """
-        metadata = self._build_metadata(**kwargs)
+        metadata, kwargs = self._build_metadata(**kwargs)
         self._df.write_parquet(file, metadata=metadata, **kwargs)
 
     def sink_parquet(
@@ -117,14 +117,16 @@ class FailureInfo(Generic[S]):
             Be aware that this method suffers from the same limitations as
             :meth:`Schema.serialize`.
         """
-        metadata = self._build_metadata(**kwargs)
+        metadata, kwargs = self._build_metadata(**kwargs)
         self._lf.sink_parquet(file, metadata=metadata, **kwargs)
 
-    def _build_metadata(self, **kwargs: Any) -> dict[str, Any]:
+    def _build_metadata(
+        self, **kwargs: dict[str, Any]
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
         metadata = kwargs.pop("metadata", {})
         metadata[RULE_METADATA_KEY] = json.dumps(self._rule_columns)
         metadata[SCHEMA_METADATA_KEY] = self.schema.serialize()
-        return metadata
+        return metadata, kwargs
 
     @classmethod
     def read_parquet(

{dataframely-1.7.0 → dataframely-1.7.2}/pyproject.toml

@@ -19,7 +19,7 @@ description = "A declarative, polars-native data frame validation library"
 name = "dataframely"
 readme = "README.md"
 requires-python = ">=3.11"
-version = "1.7.0"
+version = "1.7.2"
 
 [project.urls]
 Documentation = "https://dataframely.readthedocs.io/"

{dataframely-1.7.0 → dataframely-1.7.2}/tests/test_failure_info.py

@@ -52,6 +52,18 @@ def test_scan_sink_parquet(tmp_path: Path) -> None:
     assert MySchema.matches(read.schema)
 
 
+def test_write_parquet_custom_metadata(tmp_path: Path) -> None:
+    df = pl.DataFrame(
+        {
+            "a": [4, 5, 6, 6, 7, 8],
+            "b": [1, 2, 3, 4, 5, 6],
+        }
+    )
+    _, failure = MySchema.filter(df)
+    failure.write_parquet(tmp_path / "failure.parquet", metadata={"custom": "test"})
+    assert pl.read_parquet_metadata(tmp_path / "failure.parquet")["custom"] == "test"
+
+
 @pytest.mark.parametrize(
     "read_fn",
     [dy.FailureInfo.read_parquet, dy.FailureInfo.scan_parquet],