Revert "UNPICK changes to review"

This reverts commit 83ac4d1.

Author: kosiew

docs/source/conf.py

@@ -83,6 +83,9 @@ def autoapi_skip_member_fn(app, what, name, obj, skip, options) -> bool:  # noqa
         # Duplicate modules (skip module-level docs to avoid duplication)
         ("module", "datafusion.col"),
         ("module", "datafusion.udf"),
+        # Private variables causing duplicate documentation
+        ("data", "datafusion.utils._PYARROW_DATASET_TYPES"),
+        ("variable", "datafusion.utils._PYARROW_DATASET_TYPES"),
         # Deprecated
         ("class", "datafusion.substrait.serde"),
         ("class", "datafusion.substrait.plan"),
@@ -91,9 +94,28 @@ def autoapi_skip_member_fn(app, what, name, obj, skip, options) -> bool:  # noqa
         ("method", "datafusion.context.SessionContext.tables"),
         ("method", "datafusion.dataframe.DataFrame.unnest_column"),
     ]
+    # Explicitly skip certain members listed above. These are either
+    # re-exports, duplicate module-level documentation, deprecated
+    # API surfaces, or private variables that would otherwise appear
+    # in the generated docs and cause confusing duplication.
+    # Keeping this explicit list avoids surprising entries in the
+    # AutoAPI output and gives us a single place to opt-out items
+    # when we intentionally hide them from the docs.
     if (what, name) in skip_contents:
         skip = True
 
+    # Skip private module-level names (those whose final component
+    # starts with an underscore) when AutoAPI is rendering data or
+    # variable entries. Many internal module-level constants are
+    # implementation details (for example private pyarrow dataset type
+    # mappings) that would otherwise be emitted as top-level "data"
+    # or "variable" docs. Filtering them here avoids noisy,
+    # duplicate, or implementation-specific entries in the public
+    # documentation while still allowing public members and types to
+    # be documented normally.
+    if name.split(".")[-1].startswith("_") and what in ("data", "variable"):
+        skip = True
+
     return skip
 
 

docs/source/contributor-guide/ffi.rst

@@ -34,7 +34,7 @@ as performant as possible and to utilize the features of DataFusion, you may dec
 your source in Rust and then expose it through `PyO3 <https://pyo3.rs>`_ as a Python library.
 
 At first glance, it may appear the best way to do this is to add the ``datafusion-python``
-crate as a dependency, provide a ``PyTable``, and then to register it with the 
+crate as a dependency, produce a DataFusion table in Rust, and then register it with the
 ``SessionContext``. Unfortunately, this will not work.
 
 When you produce your code as a Python library and it needs to interact with the DataFusion

docs/source/user-guide/data-sources.rst

@@ -152,13 +152,22 @@ as Delta Lake. This will require a recent version of
 .. code-block:: python
 
     from deltalake import DeltaTable
+    from datafusion import TableProvider
 
     delta_table = DeltaTable("path_to_table")
-    ctx.register_table_provider("my_delta_table", delta_table)
+    provider = TableProvider.from_capsule(delta_table.__datafusion_table_provider__())
+    ctx.register_table("my_delta_table", provider)
     df = ctx.table("my_delta_table")
     df.show()
 
-On older versions of ``deltalake`` (prior to 0.22) you can use the 
+.. note::
+
+   :py:meth:`~datafusion.context.SessionContext.register_table_provider` is
+   deprecated. Use
+   :py:meth:`~datafusion.context.SessionContext.register_table` with a
+   :py:class:`~datafusion.TableProvider` instead.
+
+On older versions of ``deltalake`` (prior to 0.22) you can use the
 `Arrow DataSet <https://arrow.apache.org/docs/python/generated/pyarrow.dataset.Dataset.html>`_
 interface to import to DataFusion, but this does not support features such as filter push down
 which can lead to a significant performance difference.

docs/source/user-guide/io/table_provider.rst

@@ -39,20 +39,47 @@ A complete example can be found in the `examples folder <https://github.com/apac
         ) -> PyResult<Bound<'py, PyCapsule>> {
             let name = CString::new("datafusion_table_provider").unwrap();
 
-            let provider = Arc::new(self.clone())
-                .map_err(|e| PyRuntimeError::new_err(e.to_string()))?;
-            let provider = FFI_TableProvider::new(Arc::new(provider), false);
+            let provider = Arc::new(self.clone());
+            let provider = FFI_TableProvider::new(provider, false, None);
 
             PyCapsule::new_bound(py, provider, Some(name.clone()))
         }
     }
 
-Once you have this library available, in python you can register your table provider
-to the ``SessionContext``.
+Once you have this library available, you can construct a
+:py:class:`~datafusion.TableProvider` in Python and register it with the
+``SessionContext``.  Table providers can be created either from the PyCapsule exposed by
+your Rust provider or from an existing :py:class:`~datafusion.dataframe.DataFrame`.
+Call the provider's ``__datafusion_table_provider__()`` method to obtain the capsule
+before constructing a ``TableProvider``. The ``TableProvider.from_view()`` helper is
+deprecated; instead use ``TableProvider.from_dataframe()`` or ``DataFrame.into_view()``.
+
+.. note::
+
+   :py:meth:`~datafusion.context.SessionContext.register_table_provider` is
+   deprecated. Use
+   :py:meth:`~datafusion.context.SessionContext.register_table` with the
+   resulting :py:class:`~datafusion.TableProvider` instead.
 
 .. code-block:: python
 
+    from datafusion import SessionContext, TableProvider
+
+    ctx = SessionContext()
     provider = MyTableProvider()
-    ctx.register_table_provider("my_table", provider)
 
-    ctx.table("my_table").show()
+    capsule = provider.__datafusion_table_provider__()
+    capsule_provider = TableProvider.from_capsule(capsule)
+
+    df = ctx.from_pydict({"a": [1]})
+    view_provider = TableProvider.from_dataframe(df)
+    # or: view_provider = df.into_view()
+
+    ctx.register_table("capsule_table", capsule_provider)
+    ctx.register_table("view_table", view_provider)
+
+    ctx.table("capsule_table").show()
+    ctx.table("view_table").show()
+
+Both ``TableProvider.from_capsule()`` and ``TableProvider.from_dataframe()`` create
+table providers that can be registered with the SessionContext using ``register_table()``.

examples/datafusion-ffi-example/python/tests/_test_table_function.py

@@ -53,7 +53,7 @@ def test_ffi_table_function_call_directly():
     table_udtf = udtf(table_func, "my_table_func")
 
     my_table = table_udtf()
-    ctx.register_table_provider("t", my_table)
+    ctx.register_table("t", my_table)
     result = ctx.table("t").collect()
 
     assert len(result) == 2

examples/datafusion-ffi-example/python/tests/_test_table_provider.py

@@ -18,14 +18,16 @@
 from __future__ import annotations
 
 import pyarrow as pa
-from datafusion import SessionContext
+from datafusion import SessionContext, TableProvider
 from datafusion_ffi_example import MyTableProvider
 
 
 def test_table_loading():
     ctx = SessionContext()
     table = MyTableProvider(3, 2, 4)
-    ctx.register_table_provider("t", table)
+    ctx.register_table(
+        "t", TableProvider.from_capsule(table.__datafusion_table_provider__())
+    )
     result = ctx.table("t").collect()
 
     assert len(result) == 4

python/datafusion/__init__.py

@@ -28,17 +28,16 @@
 try:
     import importlib.metadata as importlib_metadata
 except ImportError:
-    import importlib_metadata
+    import importlib_metadata  # type: ignore[import]
 
+# Public submodules
 from . import functions, object_store, substrait, unparser
 
 # The following imports are okay to remain as opaque to the user.
-from ._internal import Config
+from ._internal import EXPECTED_PROVIDER_MSG, Config
 from .catalog import Catalog, Database, Table
 from .col import col, column
-from .common import (
-    DFSchema,
-)
+from .common import DFSchema
 from .context import (
     RuntimeEnvBuilder,
     SessionConfig,
@@ -47,13 +46,11 @@
 )
 from .dataframe import DataFrame, ParquetColumnOptions, ParquetWriterOptions
 from .dataframe_formatter import configure_formatter
-from .expr import (
-    Expr,
-    WindowFrame,
-)
+from .expr import Expr, WindowFrame
 from .io import read_avro, read_csv, read_json, read_parquet
 from .plan import ExecutionPlan, LogicalPlan
 from .record_batch import RecordBatch, RecordBatchStream
+from .table_provider import TableProvider
 from .user_defined import (
     Accumulator,
     AggregateUDF,
@@ -69,6 +66,7 @@
 __version__ = importlib_metadata.version(__name__)
 
 __all__ = [
+    "EXPECTED_PROVIDER_MSG",
     "Accumulator",
     "AggregateUDF",
     "Catalog",
@@ -90,6 +88,7 @@
     "SessionContext",
     "Table",
     "TableFunction",
+    "TableProvider",
     "WindowFrame",
     "WindowUDF",
     "catalog",

python/datafusion/catalog.py

@@ -23,10 +23,14 @@
 from typing import TYPE_CHECKING, Protocol
 
 import datafusion._internal as df_internal
+from datafusion.utils import _normalize_table_provider
 
 if TYPE_CHECKING:
     import pyarrow as pa
 
+    from datafusion import TableProvider
+    from datafusion.context import TableProviderExportable
+
 try:
     from warnings import deprecated  # Python 3.13+
 except ImportError:
@@ -82,7 +86,11 @@ def database(self, name: str = "public") -> Schema:
         """Returns the database with the given ``name`` from this catalog."""
         return self.schema(name)
 
-    def register_schema(self, name, schema) -> Schema | None:
+    def register_schema(
+        self,
+        name: str,
+        schema: Schema | SchemaProvider | SchemaProviderExportable,
+    ) -> Schema | None:
         """Register a schema with this catalog."""
         if isinstance(schema, Schema):
             return self.catalog.register_schema(name, schema._raw_schema)
@@ -122,11 +130,16 @@ def table(self, name: str) -> Table:
         """Return the table with the given ``name`` from this schema."""
         return Table(self._raw_schema.table(name))
 
-    def register_table(self, name, table) -> None:
-        """Register a table provider in this schema."""
-        if isinstance(table, Table):
-            return self._raw_schema.register_table(name, table.table)
-        return self._raw_schema.register_table(name, table)
+    def register_table(
+        self, name: str, table: Table | TableProvider | TableProviderExportable
+    ) -> None:
+        """Register a table or table provider in this schema.
+
+        Objects implementing ``__datafusion_table_provider__`` are also supported
+        and treated as :class:`TableProvider` instances.
+        """
+        provider = _normalize_table_provider(table)
+        return self._raw_schema.register_table(name, provider)
 
     def deregister_table(self, name: str) -> None:
         """Deregister a table provider from this schema."""
@@ -219,14 +232,19 @@ def table(self, name: str) -> Table | None:
         """Retrieve a specific table from this schema."""
         ...
 
-    def register_table(self, name: str, table: Table) -> None:  # noqa: B027
-        """Add a table from this schema.
+    def register_table(  # noqa: B027
+        self, name: str, table: Table | TableProvider | TableProviderExportable
+    ) -> None:
+        """Add a table to this schema.
 
         This method is optional. If your schema provides a fixed list of tables, you do
         not need to implement this method.
+
+        Objects implementing ``__datafusion_table_provider__`` are also supported
+        and treated as :class:`TableProvider` instances.
         """
 
-    def deregister_table(self, name, cascade: bool) -> None:  # noqa: B027
+    def deregister_table(self, name: str, cascade: bool) -> None:  # noqa: B027
         """Remove a table from this schema.
 
         This method is optional. If your schema provides a fixed list of tables, you do

python/datafusion/context.py

@@ -29,11 +29,11 @@
 
 import pyarrow as pa
 
-from datafusion.catalog import Catalog, CatalogProvider, Table
+from datafusion.catalog import Catalog
 from datafusion.dataframe import DataFrame
-from datafusion.expr import SortKey, sort_list_to_raw_sort_list
+from datafusion.expr import sort_list_to_raw_sort_list
 from datafusion.record_batch import RecordBatchStream
-from datafusion.user_defined import AggregateUDF, ScalarUDF, TableFunction, WindowUDF
+from datafusion.utils import _normalize_table_provider
 
 from ._internal import RuntimeEnvBuilder as RuntimeEnvBuilderInternal
 from ._internal import SessionConfig as SessionConfigInternal
@@ -48,7 +48,16 @@
     import pandas as pd
     import polars as pl  # type: ignore[import]
 
+    from datafusion import TableProvider
+    from datafusion.catalog import CatalogProvider, Table
+    from datafusion.expr import SortKey
     from datafusion.plan import ExecutionPlan, LogicalPlan
+    from datafusion.user_defined import (
+        AggregateUDF,
+        ScalarUDF,
+        TableFunction,
+        WindowUDF,
+    )
 
 
 class ArrowStreamExportable(Protocol):
@@ -733,7 +742,7 @@ def from_polars(self, data: pl.DataFrame, name: str | None = None) -> DataFrame:
     # https://github.com/apache/datafusion-python/pull/1016#discussion_r1983239116
     # is the discussion on how we arrived at adding register_view
     def register_view(self, name: str, df: DataFrame) -> None:
-        """Register a :py:class: `~datafusion.detaframe.DataFrame` as a view.
+        """Register a :py:class:`~datafusion.dataframe.DataFrame` as a view.
 
         Args:
             name (str): The name to register the view under.
@@ -742,16 +751,29 @@ def register_view(self, name: str, df: DataFrame) -> None:
         view = df.into_view()
         self.ctx.register_table(name, view)
 
-    def register_table(self, name: str, table: Table) -> None:
-        """Register a :py:class: `~datafusion.catalog.Table` as a table.
+    def register_table(
+        self, name: str, table: Table | TableProvider | TableProviderExportable
+    ) -> None:
+        """Register a Table or TableProvider.
 
-        The registered table can be referenced from SQL statement executed against.
+        The registered table can be referenced from SQL statements executed against
+        this context.
+
+        Plain :py:class:`~datafusion.dataframe.DataFrame` objects are not supported;
+        convert them first with :meth:`datafusion.dataframe.DataFrame.into_view` or
+        :meth:`datafusion.TableProvider.from_dataframe`.
+
+        Objects implementing ``__datafusion_table_provider__`` are also supported
+        and treated as :py:class:`~datafusion.TableProvider` instances.
 
         Args:
             name: Name of the resultant table.
-            table: DataFusion table to add to the session context.
+            table: DataFusion :class:`Table`, :class:`TableProvider`, or any object
+                implementing ``__datafusion_table_provider__`` to add to the session
+                context.
         """
-        self.ctx.register_table(name, table.table)
+        provider = _normalize_table_provider(table)
+        self.ctx.register_table(name, provider)
 
     def deregister_table(self, name: str) -> None:
         """Remove a table from the session."""
@@ -771,14 +793,21 @@ def register_catalog_provider(
             self.ctx.register_catalog_provider(name, provider)
 
     def register_table_provider(
-        self, name: str, provider: TableProviderExportable
+        self, name: str, provider: Table | TableProvider | TableProviderExportable
     ) -> None:
         """Register a table provider.
 
-        This table provider must have a method called ``__datafusion_table_provider__``
-        which returns a PyCapsule that exposes a ``FFI_TableProvider``.
+        Deprecated: use :meth:`register_table` instead.
+
+        Objects implementing ``__datafusion_table_provider__`` are also supported
+        and treated as :py:class:`~datafusion.TableProvider` instances.
         """
-        self.ctx.register_table_provider(name, provider)
+        warnings.warn(
+            "register_table_provider is deprecated; use register_table",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        self.register_table(name, provider)
 
     def register_udtf(self, func: TableFunction) -> None:
         """Register a user defined table function."""