feat: Add name string property to dy.Column (#52)

Author: delsner

dataframely/_base_schema.py

@@ -130,6 +130,13 @@ def __new__(
 
         return super().__new__(mcs, name, bases, namespace, *args, **kwargs)
 
+    def __getattribute__(cls, name: str) -> Any:
+        val = super().__getattribute__(name)
+        # Dynamically set the name of the column if it is a `Column` instance.
+        if isinstance(val, Column):
+            val._name = val.alias or name
+        return val
+
     @staticmethod
     def _get_metadata_recursively(kls: type[object]) -> Metadata:
         result = Metadata()
@@ -145,9 +152,7 @@ def _get_metadata(source: dict[str, Any]) -> Metadata:
             k: v for k, v in source.items() if not k.startswith("__")
         }.items():
             if isinstance(value, Column):
-                if not value.alias:
-                    value.alias = attr
-                result.columns[value.alias] = value
+                result.columns[value.alias or attr] = value
             if isinstance(value, Rule):
                 # We must ensure that custom rules do not clash with internal rules.
                 if attr == "primary_key":

dataframely/columns/_base.py

@@ -68,8 +68,7 @@ def __init__(
             alias: An overwrite for this column's name which allows for using a column
                 name that is not a valid Python identifier. Especially note that setting
                 this option does _not_ allow to refer to the column with two different
-                names, the specified alias is the only valid name. If unset, dataframely
-                internally sets the alias to the column's name in the parent schema.
+                names, the specified alias is the only valid name.
             metadata: A dictionary of metadata to attach to the column.
         """
 
@@ -85,6 +84,8 @@ def __init__(
         self.check = check
         self.alias = alias
         self.metadata = metadata
+        # The name may be overridden by the schema on column access.
+        self._name = ""
 
     # ------------------------------------- DTYPE ------------------------------------ #
 
@@ -225,12 +226,15 @@ def pyarrow_dtype(self) -> pa.DataType:
 
     # ------------------------------------ HELPER ------------------------------------ #
 
+    @property
+    def name(self) -> str:
+        """Get the name of the column in a schema."""
+        return self._name
+
     @property
     def col(self) -> pl.Expr:
         """Obtain a Polars column expression for the column."""
-        if self.alias is None:
-            raise ValueError("Cannot obtain column expression if alias is ``None``.")
-        return pl.col(self.alias)
+        return pl.col(self.name)
 
     # ----------------------------------- SAMPLING ----------------------------------- #
 

tests/columns/test_alias.py

@@ -22,3 +22,17 @@ def test_validation() -> None:
 def test_create_empty() -> None:
     df = AliasSchema.create_empty()
     assert AliasSchema.is_valid(df)
+
+
+def test_alias() -> None:
+    assert AliasSchema.a.alias == "hello world: col with space!"
+
+
+def test_alias_name() -> None:
+    assert AliasSchema.a.name == "hello world: col with space!"
+
+
+def test_alias_unset() -> None:
+    no_alias_col = dy.Int32()
+    assert no_alias_col.alias is None
+    assert no_alias_col.name == ""

tests/schema/test_base.py

@@ -64,14 +64,11 @@ def test_col() -> None:
     assert MySchema.d.col.__dict__ == pl.col("e").__dict__
 
 
-def test_col_raise_if_none() -> None:
-    class InvalidSchema(dy.Schema):
-        a = dy.Integer()
-
-    # Manually override alias to be ``None``.
-    InvalidSchema.a.alias = None
-    with pytest.raises(ValueError):
-        InvalidSchema.a.col
+def test_name() -> None:
+    assert MySchema.a.name == "a"
+    assert MySchema.b.name == "b"
+    assert MySchema.c.name == "c"
+    assert MySchema.d.name == "e"
 
 
 def test_col_in_polars_expression() -> None: