Move the udf module to user_defined (#1112)

* This is a breaking change to move the module datafusion.udf to datafusion.user_defined

* Documentation updates to make the formatting more consistent with the rest of the site and to correct some errors when building the rst files using autoapi

* Set async test parameters that generate a warning when unset in pytest

* Add deprecation warning

Author: timsaucer

docs/source/conf.py

@@ -71,6 +71,7 @@
 autoapi_member_order = "groupwise"
 suppress_warnings = ["autoapi.python_import_resolution"]
 autoapi_python_class_content = "both"
+autoapi_keep_files = False  # set to True for debugging generated files
 
 
 def autoapi_skip_member_fn(app, what, name, obj, skip, options) -> bool:  # noqa: ARG001

docs/source/user-guide/common-operations/udf-and-udfa.rst

@@ -26,7 +26,7 @@ Scalar Functions
 
 When writing a user-defined function that can operate on a row by row basis, these are called Scalar
 Functions. You can define your own scalar function by calling
-:py:func:`~datafusion.udf.ScalarUDF.udf` .
+:py:func:`~datafusion.user_defined.ScalarUDF.udf` .
 
 The basic definition of a scalar UDF is a python function that takes one or more
 `pyarrow <https://arrow.apache.org/docs/python/index.html>`_ arrays and returns a single array as
@@ -93,9 +93,9 @@ converting to Python objects to do the evaluation.
 Aggregate Functions
 -------------------
 
-The :py:func:`~datafusion.udf.AggregateUDF.udaf` function allows you to define User-Defined
+The :py:func:`~datafusion.user_defined.AggregateUDF.udaf` function allows you to define User-Defined
 Aggregate Functions (UDAFs). To use this you must implement an
-:py:class:`~datafusion.udf.Accumulator` that determines how the aggregation is performed.
+:py:class:`~datafusion.user_defined.Accumulator` that determines how the aggregation is performed.
 
 When defining a UDAF there are four methods you need to implement. The ``update`` function takes the
 array(s) of input and updates the internal state of the accumulator. You should define this function
@@ -153,8 +153,8 @@ Window Functions
 ----------------
 
 To implement a User-Defined Window Function (UDWF) you must call the
-:py:func:`~datafusion.udf.WindowUDF.udwf` function using a class that implements the abstract
-class :py:class:`~datafusion.udf.WindowEvaluator`.
+:py:func:`~datafusion.user_defined.WindowUDF.udwf` function using a class that implements the abstract
+class :py:class:`~datafusion.user_defined.WindowEvaluator`.
 
 There are three methods of evaluation of UDWFs.
 
@@ -207,7 +207,7 @@ determine which evaluate functions are called.
 
     import pyarrow as pa
     from datafusion import udwf, col, SessionContext
-    from datafusion.udf import WindowEvaluator
+    from datafusion.user_defined import WindowEvaluator
 
     class ExponentialSmooth(WindowEvaluator):
         def __init__(self, alpha: float) -> None:

examples/python-udwf.py

@@ -22,7 +22,7 @@
 from datafusion import col, lit, udwf
 from datafusion import functions as f
 from datafusion.expr import WindowFrame
-from datafusion.udf import WindowEvaluator
+from datafusion.user_defined import WindowEvaluator
 
 # This example creates five different examples of user defined window functions in order
 # to demonstrate the variety of ways a user may need to implement.

pyproject.toml

@@ -63,6 +63,10 @@ exclude = [".github/**", "ci/**", ".asf.yaml"]
 locked = true
 features = ["substrait"]
 
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+
 # Enable docstring linting using the google style guide
 [tool.ruff.lint]
 select = ["ALL" ]

python/datafusion/__init__.py

@@ -51,7 +51,15 @@
 from .io import read_avro, read_csv, read_json, read_parquet
 from .plan import ExecutionPlan, LogicalPlan
 from .record_batch import RecordBatch, RecordBatchStream
-from .udf import Accumulator, AggregateUDF, ScalarUDF, WindowUDF, udaf, udf, udwf
+from .user_defined import (
+    Accumulator,
+    AggregateUDF,
+    ScalarUDF,
+    WindowUDF,
+    udaf,
+    udf,
+    udwf,
+)
 
 __version__ = importlib_metadata.version(__name__)
 

python/datafusion/context.py

@@ -30,7 +30,7 @@
 from datafusion.dataframe import DataFrame
 from datafusion.expr import Expr, SortExpr, sort_list_to_raw_sort_list
 from datafusion.record_batch import RecordBatchStream
-from datafusion.udf import AggregateUDF, ScalarUDF, WindowUDF
+from datafusion.user_defined import AggregateUDF, ScalarUDF, WindowUDF
 
 from ._internal import RuntimeEnvBuilder as RuntimeEnvBuilderInternal
 from ._internal import SessionConfig as SessionConfigInternal