Remove deprecated left semi- and anti- join APIs

cpp/CMakeLists.txt

@@ -588,7 +588,6 @@ add_library(
   src/join/mixed_join_semi.cu
   src/join/mixed_join_size_kernel.cu
   src/join/mixed_join_size_kernel_nulls.cu
-  src/join/semi_join.cu
   src/join/sort_merge_join.cu
   src/json/json_path.cu
   src/lists/contains.cu

cpp/include/cudf/join/join.hpp

@@ -201,73 +201,6 @@ full_join(cudf::table_view const& left_keys,
           rmm::cuda_stream_view stream      = cudf::get_default_stream(),
           rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
-/**
- * @brief Returns a vector of row indices corresponding to a left semi-join
- * between the specified tables.
- *
- * @deprecated Use the object-oriented filtered_join `cudf::filtered_join::anti_join` instead
- *
- * The returned vector contains the row indices from the left table
- * for which there is a matching row in the right table.
- *
- * @code{.pseudo}
- * TableA: {{0, 1, 2}}
- * TableB: {{1, 2, 3}}
- * Result: {1, 2}
- * @endcode
- *
- * @param left_keys The left table
- * @param right_keys The right table
- * @param compare_nulls Controls whether null join-key values should match or not
- * @param stream CUDA stream used for device memory operations and kernel launches
- * @param mr Device memory resource used to allocate the returned table and columns' device memory
- *
- * @return A vector `left_indices` that can be used to construct
- * the result of performing a left semi join between two tables with
- * `left_keys` and `right_keys` as the join keys .
- */
-[[deprecated]] std::unique_ptr<rmm::device_uvector<size_type>> left_semi_join(
-  cudf::table_view const& left_keys,
-  cudf::table_view const& right_keys,
-  null_equality compare_nulls       = null_equality::EQUAL,
-  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
-  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
-
-/**
- * @brief Returns a vector of row indices corresponding to a left anti join
- * between the specified tables.
- *
- * @deprecated Use the object-oriented filtered_join `cudf::filtered_join::semi_join` instead
- *
- * The returned vector contains the row indices from the left table
- * for which there is no matching row in the right table.
- *
- * @code{.pseudo}
- * TableA: {{0, 1, 2}}
- * TableB: {{1, 2, 3}}
- * Result: {0}
- * @endcode
- *
- * @throw cudf::logic_error if the number of columns in either `left_keys` or `right_keys` is 0
- *
- * @param[in] left_keys The left table
- * @param[in] right_keys The right table
- * @param[in] compare_nulls controls whether null join-key values
- * should match or not.
- * @param stream CUDA stream used for device memory operations and kernel launches
- * @param mr Device memory resource used to allocate the returned table and columns' device memory
- *
- * @return A column `left_indices` that can be used to construct
- * the result of performing a left anti join between two tables with
- * `left_keys` and `right_keys` as the join keys .
- */
-[[deprecated]] std::unique_ptr<rmm::device_uvector<size_type>> left_anti_join(
-  cudf::table_view const& left_keys,
-  cudf::table_view const& right_keys,
-  null_equality compare_nulls       = null_equality::EQUAL,
-  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
-  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
-
 /**
  * @brief Performs a cross join on two tables (`left`, `right`)
  *

java/src/main/native/src/TableJni.cpp

@@ -27,6 +27,7 @@
 #include <cudf/io/parquet.hpp>
 #include <cudf/join/conditional_join.hpp>
 #include <cudf/join/distinct_hash_join.hpp>
+#include <cudf/join/filtered_join.hpp>
 #include <cudf/join/hash_join.hpp>
 #include <cudf/join/join.hpp>
 #include <cudf/join/mixed_join.hpp>
@@ -3511,13 +3512,16 @@ Java_ai_rapids_cudf_Table_mixedFullJoinGatherMaps(JNIEnv* env,
 JNIEXPORT jlongArray JNICALL Java_ai_rapids_cudf_Table_leftSemiJoinGatherMap(
   JNIEnv* env, jclass, jlong j_left_keys, jlong j_right_keys, jboolean compare_nulls_equal)
 {
+  double constexpr load_factor = 0.5;
   return cudf::jni::join_gather_single_map(
     env,
     j_left_keys,
     j_right_keys,
     compare_nulls_equal,
-    [](cudf::table_view const& left, cudf::table_view const& right, cudf::null_equality nulleq) {
-      return cudf::left_semi_join(left, right, nulleq);
+    [load_factor](
+      cudf::table_view const& left, cudf::table_view const& right, cudf::null_equality nulleq) {
+      cudf::filtered_join obj(right, nulleq, cudf::set_as_build_table::RIGHT, load_factor);
+      return obj.semi_join(left);
     });
 }
 
@@ -3608,13 +3612,16 @@ Java_ai_rapids_cudf_Table_mixedLeftSemiJoinGatherMap(JNIEnv* env,
 JNIEXPORT jlongArray JNICALL Java_ai_rapids_cudf_Table_leftAntiJoinGatherMap(
   JNIEnv* env, jclass, jlong j_left_keys, jlong j_right_keys, jboolean compare_nulls_equal)
 {
+  double constexpr load_factor = 0.5;
   return cudf::jni::join_gather_single_map(
     env,
     j_left_keys,
     j_right_keys,
     compare_nulls_equal,
-    [](cudf::table_view const& left, cudf::table_view const& right, cudf::null_equality nulleq) {
-      return cudf::left_anti_join(left, right, nulleq);
+    [load_factor](
+      cudf::table_view const& left, cudf::table_view const& right, cudf::null_equality nulleq) {
+      cudf::filtered_join obj(right, nulleq, cudf::set_as_build_table::RIGHT, load_factor);
+      return obj.anti_join(left);
     });
 }
 

python/pylibcudf/pylibcudf/join.pxd

@@ -1,6 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
+from libcpp.memory cimport unique_ptr
+from pylibcudf.libcudf cimport join as cpp_join
 from pylibcudf.libcudf.types cimport null_equality
 from rmm.pylibrmm.stream cimport Stream
 from rmm.pylibrmm.memory_resource cimport DeviceMemoryResource
@@ -148,3 +150,6 @@ cpdef Column mixed_left_anti_join(
     Stream stream=*,
     DeviceMemoryResource mr=*,
 )
+
+cdef class FilteredJoin:
+    cdef unique_ptr[cpp_join.filtered_join] c_obj

python/pylibcudf/pylibcudf/join.pyi

@@ -1,6 +1,8 @@
-# SPDX-FileCopyrightText: Copyright (c) 2024, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
+from enum import IntEnum
+
 from rmm.pylibrmm import Stream
 from rmm.pylibrmm.memory_resource import DeviceMemoryResource
 
@@ -9,6 +11,10 @@ from pylibcudf.expressions import Expression
 from pylibcudf.table import Table
 from pylibcudf.types import NullEquality
 
+class SetAsBuildTable(IntEnum):
+    LEFT = ...
+    RIGHT = ...
+
 def inner_join(
     left_keys: Table,
     right_keys: Table,
@@ -135,3 +141,25 @@ def mixed_left_anti_join(
     stream: Stream | None = None,
     mr: DeviceMemoryResource | None = None,
 ) -> Column: ...
+
+class FilteredJoin:
+    def __init__(
+        self,
+        build: Table,
+        compare_nulls: NullEquality,
+        reuse_tbl: SetAsBuildTable,
+        load_factor: float,
+        stream: Stream | None = None,
+    ) -> None: ...
+    def semi_join(
+        self,
+        probe: Table,
+        stream: Stream | None = None,
+        mr: DeviceMemoryResource | None = None,
+    ) -> Column: ...
+    def anti_join(
+        self,
+        probe: Table,
+        stream: Stream | None = None,
+        mr: DeviceMemoryResource | None = None,
+    ) -> Column: ...