Merge branch 'branch-24.12' into strings-factory-nvbench

python/cudf/cudf/_lib/transform.pyx

@@ -3,12 +3,10 @@
 from numba.np import numpy_support
 
 import cudf
-from cudf.core._internals.expressions import parse_expression
 from cudf.core.buffer import acquire_spill_lock, as_buffer
 from cudf.utils import cudautils
 
 from pylibcudf cimport transform as plc_transform
-from pylibcudf.expressions cimport Expression
 from pylibcudf.libcudf.types cimport size_type
 
 from cudf._lib.column cimport Column
@@ -93,7 +91,7 @@ def one_hot_encode(Column input_column, Column categories):
 
 
 @acquire_spill_lock()
-def compute_column(list columns, tuple column_names, expr: str):
+def compute_column(list columns, tuple column_names, str expr):
     """Compute a new column by evaluating an expression on a set of columns.
 
     Parameters
@@ -108,12 +106,8 @@ def compute_column(list columns, tuple column_names, expr: str):
     expr : str
         The expression to evaluate.
     """
-    visitor = parse_expression(expr, column_names)
-
-    # At the end, all the stack contains is the expression to evaluate.
-    cdef Expression cudf_expr = visitor.expression
     result = plc_transform.compute_column(
         plc.Table([col.to_pylibcudf(mode="read") for col in columns]),
-        cudf_expr,
+        plc.expressions.to_expression(expr, column_names),
     )
     return Column.from_pylibcudf(result)

python/custreamz/custreamz/kafka.py

@@ -151,9 +151,14 @@ def read_gdf(
             "parquet": cudf.io.read_parquet,
         }
 
-        result = cudf_readers[message_format](
-            kafka_datasource, engine="cudf", lines=True
-        )
+        if message_format == "json":
+            result = cudf_readers[message_format](
+                kafka_datasource, engine="cudf", lines=True
+            )
+        else:
+            result = cudf_readers[message_format](
+                kafka_datasource, engine="cudf"
+            )
 
         # Close up the cudf datasource instance
         # TODO: Ideally the C++ destructor should handle the

python/pylibcudf/pylibcudf/expressions.pyi

@@ -77,3 +77,5 @@ class Operation(Expression):
         left: Expression,
         right: Expression | None = None,
     ): ...
+
+def to_expression(expr: str, column_names: tuple[str, ...]) -> Expression: ...