Migrate expressions to pylibcudf (#16056)

xref #15162 Migrates expresions to use pylibcudf. Authors: - Thomas Li (https://github.com/lithomas1) Approvers: - Vyas Ramasubramani (https://github.com/vyasr) - Lawrence Mitchell (https://github.com/wence-) URL: #16056
rapidsai · Jul 16, 2024 · 6a954e2 · 6a954e2
1 parent 6219110
commit 6a954e2
Show file tree

Hide file tree

Showing 18 changed files with 335 additions and 237 deletions.
diff --git a/docs/cudf/source/user_guide/api_docs/pylibcudf/datetime.rst b/docs/cudf/source/user_guide/api_docs/pylibcudf/datetime.rst
@@ -1,6 +1,6 @@
-=======
-copying
-=======
+========
+datetime
+========
 
 .. automodule:: cudf._lib.pylibcudf.datetime
    :members:
diff --git a/docs/cudf/source/user_guide/api_docs/pylibcudf/expressions.rst b/docs/cudf/source/user_guide/api_docs/pylibcudf/expressions.rst
@@ -0,0 +1,6 @@
+===========
+expressions
+===========
+
+.. automodule:: cudf._lib.pylibcudf.expressions
+   :members:
diff --git a/docs/cudf/source/user_guide/api_docs/pylibcudf/index.rst b/docs/cudf/source/user_guide/api_docs/pylibcudf/index.rst
@@ -15,6 +15,7 @@ This page provides API documentation for pylibcudf.
     concatenate
     copying
     datetime
+    expressions
     filling
     gpumemoryview
     groupby

diff --git a/python/cudf/cudf/_lib/CMakeLists.txt b/python/cudf/cudf/_lib/CMakeLists.txt
@@ -21,7 +21,6 @@ set(cython_sources
     copying.pyx
     csv.pyx
     datetime.pyx
-    expressions.pyx
     filling.pyx
     groupby.pyx
     hash.pyx

diff --git a/python/cudf/cudf/_lib/__init__.py b/python/cudf/cudf/_lib/__init__.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, NVIDIA CORPORATION.
 import numpy as np
 
 from . import (
@@ -8,7 +8,6 @@
     copying,
     csv,
     datetime,
-    expressions,
     filling,
     groupby,
     hash,

diff --git a/python/cudf/cudf/_lib/expressions.pyx b/python/cudf/cudf/_lib/expressions.pyx
diff --git a/python/cudf/cudf/_lib/parquet.pyx b/python/cudf/cudf/_lib/parquet.pyx
@@ -37,12 +37,12 @@ cimport cudf._lib.pylibcudf.libcudf.io.data_sink as cudf_io_data_sink
 cimport cudf._lib.pylibcudf.libcudf.io.types as cudf_io_types
 cimport cudf._lib.pylibcudf.libcudf.types as cudf_types
 from cudf._lib.column cimport Column
-from cudf._lib.expressions cimport Expression
 from cudf._lib.io.utils cimport (
     make_sinks_info,
     make_source_info,
     update_struct_field_names,
 )
+from cudf._lib.pylibcudf.expressions cimport Expression
 from cudf._lib.pylibcudf.io.datasource cimport NativeFileDatasource
 from cudf._lib.pylibcudf.libcudf.expressions cimport expression
 from cudf._lib.pylibcudf.libcudf.io.parquet cimport (

diff --git a/python/cudf/cudf/_lib/pylibcudf/CMakeLists.txt b/python/cudf/cudf/_lib/pylibcudf/CMakeLists.txt
@@ -20,6 +20,7 @@ set(cython_sources
     concatenate.pyx
     copying.pyx
     datetime.pyx
+    expressions.pyx
     filling.pyx
     gpumemoryview.pyx
     groupby.pyx

diff --git a/python/cudf/cudf/_lib/pylibcudf/__init__.pxd b/python/cudf/cudf/_lib/pylibcudf/__init__.pxd
@@ -8,6 +8,7 @@ from . cimport (
     concatenate,
     copying,
     datetime,
+    expressions,
     filling,
     groupby,
     join,

diff --git a/python/cudf/cudf/_lib/pylibcudf/__init__.py b/python/cudf/cudf/_lib/pylibcudf/__init__.py
@@ -7,6 +7,7 @@
     concatenate,
     copying,
     datetime,
+    expressions,
     filling,
     groupby,
     interop,

diff --git a/python/cudf/cudf/_lib/expressions.pxd → .../cudf/cudf/_lib/pylibcudf/expressions.pxd b/python/cudf/cudf/_lib/expressions.pxd → .../cudf/cudf/_lib/pylibcudf/expressions.pxd
@@ -1,36 +1,31 @@
-# Copyright (c) 2022-2024, NVIDIA CORPORATION.
-
-from libc.stdint cimport int32_t, int64_t
+# Copyright (c) 2024, NVIDIA CORPORATION.
 from libcpp.memory cimport unique_ptr
+from libcpp.string cimport string
 
 from cudf._lib.pylibcudf.libcudf.expressions cimport (
-    column_reference,
+    ast_operator,
     expression,
-    literal,
-    operation,
-)
-from cudf._lib.pylibcudf.libcudf.scalar.scalar cimport (
-    numeric_scalar,
-    scalar,
-    string_scalar,
-    timestamp_scalar,
+    table_reference,
 )
 
+from .scalar cimport Scalar
+
 
 cdef class Expression:
     cdef unique_ptr[expression] c_obj
 
-
 cdef class Literal(Expression):
-    cdef unique_ptr[scalar] c_scalar
-
+    # Hold on to input scalar so it doesn't get gc'ed
+    cdef Scalar scalar
 
 cdef class ColumnReference(Expression):
     pass
 
-
 cdef class Operation(Expression):
-    pass
+    # Hold on to the input expressions so
+    # they don't get gc'ed
+    cdef Expression right
+    cdef Expression left
 
 cdef class ColumnNameReference(Expression):
     pass