Move hash type declarations to hashing.hpp (#10320)

Move the `hash_id` and `DEFAULT_HASH_SEED` declarations from `types.hpp` to `hashing.hpp`. Authors: - David Wendt (https://github.com/davidwendt) Approvers: - GALI PREM SAGAR (https://github.com/galipremsagar) - https://github.com/brandon-b-miller - Bradley Dice (https://github.com/bdice) URL: #10320
rapidsai · Feb 18, 2022 · ec614ac · ec614ac
1 parent b28bad6
commit ec614ac
Show file tree

Hide file tree

Showing 7 changed files with 36 additions and 36 deletions.
diff --git a/cpp/include/cudf/detail/utilities/hash_functions.cuh b/cpp/include/cudf/detail/utilities/hash_functions.cuh
@@ -21,6 +21,7 @@
 #include <cudf/column/column_device_view.cuh>
 #include <cudf/detail/utilities/assert.cuh>
 #include <cudf/fixed_point/fixed_point.hpp>
+#include <cudf/hashing.hpp>
 #include <cudf/strings/string_view.cuh>
 #include <cudf/types.hpp>
 

diff --git a/cpp/include/cudf/hashing.hpp b/cpp/include/cudf/hashing.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -17,7 +17,6 @@
 
 #include <cudf/table/table.hpp>
 #include <cudf/table/table_view.hpp>
-#include <cudf/utilities/span.hpp>
 
 namespace cudf {
 /**
@@ -26,6 +25,22 @@ namespace cudf {
  * @file
  */
 
+/**
+ *  @brief Identifies the hash function to be used
+ */
+enum class hash_id {
+  HASH_IDENTITY = 0,    ///< Identity hash function that simply returns the key to be hashed
+  HASH_MURMUR3,         ///< Murmur3 hash function
+  HASH_MD5,             ///< MD5 hash function
+  HASH_SERIAL_MURMUR3,  ///< Serial Murmur3 hash function
+  HASH_SPARK_MURMUR3    ///< Spark Murmur3 hash function
+};
+
+/**
+ * @brief The default seed value for hash functions
+ */
+static constexpr uint32_t DEFAULT_HASH_SEED = 0;
+
 /**
  * @brief Computes the hash value of each row in the input set of columns.
  *

diff --git a/cpp/include/cudf/partitioning.hpp b/cpp/include/cudf/partitioning.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -16,7 +16,7 @@
 
 #pragma once
 
-#include <cudf/types.hpp>
+#include <cudf/hashing.hpp>
 
 #include <rmm/cuda_stream_view.hpp>
 

diff --git a/cpp/include/cudf/types.hpp b/cpp/include/cudf/types.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2018-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -326,21 +326,5 @@ inline bool operator!=(data_type const& lhs, data_type const& rhs) { return !(lh
  */
 std::size_t size_of(data_type t);
 
-/**
- *  @brief Identifies the hash function to be used
- */
-enum class hash_id {
-  HASH_IDENTITY = 0,    ///< Identity hash function that simply returns the key to be hashed
-  HASH_MURMUR3,         ///< Murmur3 hash function
-  HASH_MD5,             ///< MD5 hash function
-  HASH_SERIAL_MURMUR3,  ///< Serial Murmur3 hash function
-  HASH_SPARK_MURMUR3    ///< Spark Murmur3 hash function
-};
-
-/**
- * @brief The default seed value for hash functions
- */
-static constexpr uint32_t DEFAULT_HASH_SEED = 0;
-
 /** @} */
 }  // namespace cudf
diff --git a/python/cudf/cudf/_lib/cpp/hash.pxd b/python/cudf/cudf/_lib/cpp/hash.pxd
@@ -1,18 +1,25 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
 from libc.stdint cimport uint32_t
 from libcpp.memory cimport unique_ptr
 from libcpp.vector cimport vector
 
-cimport cudf._lib.cpp.types as libcudf_types
 from cudf._lib.cpp.column.column cimport column
 from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view
 
 
 cdef extern from "cudf/hashing.hpp" namespace "cudf" nogil:
+
+    ctypedef enum hash_id "cudf::hash_id":
+        HASH_IDENTITY "cudf::hash_id::HASH_IDENTITY"
+        HASH_MURMUR3 "cudf::hash_id::HASH_MURMUR3"
+        HASH_MD5 "cudf::hash_id::HASH_MD5"
+        HASH_SERIAL_MURMUR3 "cudf::hash_id::HASH_SERIAL_MURMUR3"
+        HASH_SPARK_MURMUR3 "cudf::hash_id::HASH_SPARK_MURMUR3"
+
     cdef unique_ptr[column] hash "cudf::hash" (
         const table_view& input,
-        const libcudf_types.hash_id hash_function,
+        const hash_id hash_function,
         const uint32_t seed
     ) except +
diff --git a/python/cudf/cudf/_lib/cpp/types.pxd b/python/cudf/cudf/_lib/cpp/types.pxd
@@ -81,13 +81,6 @@ cdef extern from "cudf/types.hpp" namespace "cudf" nogil:
         DECIMAL64              "cudf::type_id::DECIMAL64"
         DECIMAL128             "cudf::type_id::DECIMAL128"
 
-    ctypedef enum hash_id "cudf::hash_id":
-        HASH_IDENTITY "cudf::hash_id::HASH_IDENTITY"
-        HASH_MURMUR3 "cudf::hash_id::HASH_MURMUR3"
-        HASH_MD5 "cudf::hash_id::HASH_MD5"
-        HASH_SERIAL_MURMUR3 "cudf::hash_id::HASH_SERIAL_MURMUR3"
-        HASH_SPARK_MURMUR3 "cudf::hash_id::HASH_SPARK_MURMUR3"
-
     cdef cppclass data_type:
         data_type() except +
         data_type(const data_type&) except +

diff --git a/python/cudf/cudf/_lib/hash.pyx b/python/cudf/cudf/_lib/hash.pyx
@@ -1,4 +1,4 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
 from libc.stdint cimport uint32_t
 from libcpp cimport bool
@@ -10,7 +10,7 @@ from libcpp.vector cimport vector
 cimport cudf._lib.cpp.types as libcudf_types
 from cudf._lib.column cimport Column
 from cudf._lib.cpp.column.column cimport column
-from cudf._lib.cpp.hash cimport hash as cpp_hash
+from cudf._lib.cpp.hash cimport hash as cpp_hash, hash_id as cpp_hash_id
 from cudf._lib.cpp.partitioning cimport hash_partition as cpp_hash_partition
 from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view
@@ -58,11 +58,11 @@ def hash(source_table, str method, int seed=0):
     cdef table_view c_source_view = table_view_from_table(
         source_table, ignore_index=True)
     cdef unique_ptr[column] c_result
-    cdef libcudf_types.hash_id c_hash_function
+    cdef cpp_hash_id c_hash_function
     if method == "murmur3":
-        c_hash_function = libcudf_types.hash_id.HASH_MURMUR3
+        c_hash_function = cpp_hash_id.HASH_MURMUR3
     elif method == "md5":
-        c_hash_function = libcudf_types.hash_id.HASH_MD5
+        c_hash_function = cpp_hash_id.HASH_MD5
     else:
         raise ValueError(f"Unsupported hash function: {method}")
     with nogil: