Refactor string conversion check

cpp/include/cudf/strings/char_types/char_types.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2020, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2021, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -146,82 +146,6 @@ std::unique_ptr<column> filter_characters_of_type(
   string_character_types types_to_keep = string_character_types::ALL_TYPES,
   rmm::mr::device_memory_resource* mr  = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a boolean column identifying strings in which all
- * characters are valid for conversion to integers.
- *
- * The output row entry will be set to `true` if the corresponding string element
- * has at least one character in [-+0-9].
- *
- * @code{.pseudo}
- * Example:
- * s = ['123', '-456', '', 'A', '+7']
- * b = s.is_integer(s)
- * b is [true, true, false, false, true]
- * @endcode
- *
- * Any null row results in a null entry for that row in the output column.
- *
- * @param strings Strings instance for this operation.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New column of boolean results for each string.
- */
-std::unique_ptr<column> is_integer(
-  strings_column_view const& strings,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
-/**
- * @brief Returns `true` if all strings contain
- * characters that are valid for conversion to integers.
- *
- * This function will return `true` if all string elements
- * has at least one character in [-+0-9].
- *
- * Any null entry or empty string will cause this function to return `false`.
- *
- * @param strings Strings instance for this operation.
- * @return true if all string are valid
- */
-bool all_integer(strings_column_view const& strings);
-
-/**
- * @brief Returns a boolean column identifying strings in which all
- * characters are valid for conversion to floats.
- *
- * The output row entry will be set to `true` if the corresponding string element
- * has at least one character in [-+0-9eE.].
- *
- * @code{.pseudo}
- * Example:
- * s = ['123', '-456', '', 'A', '+7', '8.9' '3.7e+5']
- * b = s.is_float(s)
- * b is [true, true, false, false, true, true, true]
- * @endcode
- *
- * Any null row results in a null entry for that row in the output column.
- *
- * @param strings Strings instance for this operation.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New column of boolean results for each string.
- */
-std::unique_ptr<column> is_float(
-  strings_column_view const& strings,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
-/**
- * @brief Returns `true` if all strings contain
- * characters that are valid for conversion to floats.
- *
- * This function will return `true` if all string elements
- * has at least one character in [-+0-9eE.].
- *
- * Any null entry or empty string will cause this function to return `false`.
- *
- * @param strings Strings instance for this operation.
- * @return true if all string are valid
- */
-bool all_float(strings_column_view const& strings);
-
 /** @} */  // end of doxygen group
 }  // namespace strings
 }  // namespace cudf

cpp/include/cudf/strings/convert/convert_floats.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019, NVIDIA CORPORATION.
+ * Copyright (c) 2021, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -68,6 +68,30 @@ std::unique_ptr<column> from_floats(
   column_view const& floats,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
+/**
+ * @brief Returns a boolean column identifying strings in which all
+ * characters are valid for conversion to floats.
+ *
+ * The output row entry will be set to `true` if the corresponding string element
+ * has at least one character in [-+0-9eE.].
+ *
+ * @code{.pseudo}
+ * Example:
+ * s = ['123', '-456', '', 'A', '+7', '8.9' '3.7e+5']
+ * b = s.is_float(s)
+ * b is [true, true, false, false, true, true, true]
+ * @endcode
+ *
+ * Any null row results in a null entry for that row in the output column.
+ *
+ * @param strings Strings instance for this operation.
+ * @param mr Device memory resource used to allocate the returned column's device memory.
+ * @return New column of boolean results for each string.
+ */
+std::unique_ptr<column> is_float(
+  strings_column_view const& strings,
+  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+
 /** @} */  // end of doxygen group
 }  // namespace strings
 }  // namespace cudf

cpp/include/cudf/strings/convert/convert_integers.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019, NVIDIA CORPORATION.
+ * Copyright (c) 2021, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -73,6 +73,30 @@ std::unique_ptr<column> from_integers(
   column_view const& integers,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
+/**
+ * @brief Returns a boolean column identifying strings in which all
+ * characters are valid for conversion to integers.
+ *
+ * The output row entry will be set to `true` if the corresponding string element
+ * has at least one character in [-+0-9].
+ *
+ * @code{.pseudo}
+ * Example:
+ * s = ['123', '-456', '', 'A', '+7']
+ * b = s.is_integer(s)
+ * b is [true, true, false, false, true]
+ * @endcode
+ *
+ * Any null row results in a null entry for that row in the output column.
+ *
+ * @param strings Strings instance for this operation.
+ * @param mr Device memory resource used to allocate the returned column's device memory.
+ * @return New column of boolean results for each string.
+ */
+std::unique_ptr<column> is_integer(
+  strings_column_view const& strings,
+  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+
 /**
  * @brief Returns a new integer numeric column parsing hexadecimal values from the
  * provided strings column.

cpp/src/strings/char_types/char_types.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2020, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2021, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -186,91 +186,6 @@ std::unique_ptr<column> filter_characters_of_type(strings_column_view const& str
                              mr);
 }
 
-std::unique_ptr<column> is_integer(
-  strings_column_view const& strings,
-  rmm::cuda_stream_view stream,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource())
-{
-  auto strings_column = column_device_view::create(strings.parent(), stream);
-  auto d_column       = *strings_column;
-  // create output column
-  auto results   = make_numeric_column(data_type{type_id::BOOL8},
-                                     strings.size(),
-                                     cudf::detail::copy_bitmask(strings.parent(), stream, mr),
-                                     strings.null_count(),
-                                     stream,
-                                     mr);
-  auto d_results = results->mutable_view().data<bool>();
-  thrust::transform(rmm::exec_policy(stream),
-                    thrust::make_counting_iterator<size_type>(0),
-                    thrust::make_counting_iterator<size_type>(strings.size()),
-                    d_results,
-                    [d_column] __device__(size_type idx) {
-                      if (d_column.is_null(idx)) return false;
-                      return string::is_integer(d_column.element<string_view>(idx));
-                    });
-  results->set_null_count(strings.null_count());
-  return results;
-}
-
-bool all_integer(strings_column_view const& strings, rmm::cuda_stream_view stream)
-{
-  auto strings_column  = column_device_view::create(strings.parent(), stream);
-  auto d_column        = *strings_column;
-  auto transformer_itr = thrust::make_transform_iterator(
-    thrust::make_counting_iterator<size_type>(0), [d_column] __device__(size_type idx) {
-      if (d_column.is_null(idx)) return false;
-      return string::is_integer(d_column.element<string_view>(idx));
-    });
-  return thrust::all_of(rmm::exec_policy(stream),
-                        transformer_itr,
-                        transformer_itr + strings.size(),
-                        thrust::identity<bool>());
-}
-
-std::unique_ptr<column> is_float(
-  strings_column_view const& strings,
-  rmm::cuda_stream_view stream,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource())
-{
-  auto strings_column = column_device_view::create(strings.parent(), stream);
-  auto d_column       = *strings_column;
-  // create output column
-  auto results   = make_numeric_column(data_type{type_id::BOOL8},
-                                     strings.size(),
-                                     cudf::detail::copy_bitmask(strings.parent(), stream, mr),
-                                     strings.null_count(),
-                                     stream,
-                                     mr);
-  auto d_results = results->mutable_view().data<bool>();
-  // check strings for valid float chars
-  thrust::transform(rmm::exec_policy(stream),
-                    thrust::make_counting_iterator<size_type>(0),
-                    thrust::make_counting_iterator<size_type>(strings.size()),
-                    d_results,
-                    [d_column] __device__(size_type idx) {
-                      if (d_column.is_null(idx)) return false;
-                      return string::is_float(d_column.element<string_view>(idx));
-                    });
-  results->set_null_count(strings.null_count());
-  return results;
-}
-
-bool all_float(strings_column_view const& strings, rmm::cuda_stream_view stream)
-{
-  auto strings_column  = column_device_view::create(strings.parent(), stream);
-  auto d_column        = *strings_column;
-  auto transformer_itr = thrust::make_transform_iterator(
-    thrust::make_counting_iterator<size_type>(0), [d_column] __device__(size_type idx) {
-      if (d_column.is_null(idx)) return false;
-      return string::is_float(d_column.element<string_view>(idx));
-    });
-  return thrust::all_of(rmm::exec_policy(stream),
-                        transformer_itr,
-                        transformer_itr + strings.size(),
-                        thrust::identity<bool>());
-}
-
 }  // namespace detail
 
 // external API
@@ -295,31 +210,5 @@ std::unique_ptr<column> filter_characters_of_type(strings_column_view const& str
     strings, types_to_remove, replacement, types_to_keep, rmm::cuda_stream_default, mr);
 }
 
-std::unique_ptr<column> is_integer(strings_column_view const& strings,
-                                   rmm::mr::device_memory_resource* mr)
-{
-  CUDF_FUNC_RANGE();
-  return detail::is_integer(strings, rmm::cuda_stream_default, mr);
-}
-
-std::unique_ptr<column> is_float(strings_column_view const& strings,
-                                 rmm::mr::device_memory_resource* mr)
-{
-  CUDF_FUNC_RANGE();
-  return detail::is_float(strings, rmm::cuda_stream_default, mr);
-}
-
-bool all_integer(strings_column_view const& strings)
-{
-  CUDF_FUNC_RANGE();
-  return detail::all_integer(strings, rmm::cuda_stream_default);
-}
-
-bool all_float(strings_column_view const& strings)
-{
-  CUDF_FUNC_RANGE();
-  return detail::all_float(strings, rmm::cuda_stream_default);
-}
-
 }  // namespace strings
 }  // namespace cudf

cpp/src/strings/convert/convert_floats.cu

@@ -21,6 +21,7 @@
 #include <cudf/strings/convert/convert_floats.hpp>
 #include <cudf/strings/detail/converters.hpp>
 #include <cudf/strings/detail/utilities.hpp>
+#include <cudf/strings/string.cuh>
 #include <cudf/strings/string_view.cuh>
 #include <cudf/strings/strings_column_view.hpp>
 #include <cudf/utilities/traits.hpp>
@@ -536,12 +537,50 @@ std::unique_ptr<column> from_floats(column_view const& floats,
 }  // namespace detail
 
 // external API
-
 std::unique_ptr<column> from_floats(column_view const& floats, rmm::mr::device_memory_resource* mr)
 {
   CUDF_FUNC_RANGE();
   return detail::from_floats(floats, rmm::cuda_stream_default, mr);
 }
 
+namespace detail {
+std::unique_ptr<column> is_float(
+  strings_column_view const& strings,
+  rmm::cuda_stream_view stream,
+  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource())
+{
+  auto strings_column = column_device_view::create(strings.parent(), stream);
+  auto d_column       = *strings_column;
+  // create output column
+  auto results   = make_numeric_column(data_type{type_id::BOOL8},
+                                     strings.size(),
+                                     cudf::detail::copy_bitmask(strings.parent(), stream, mr),
+                                     strings.null_count(),
+                                     stream,
+                                     mr);
+  auto d_results = results->mutable_view().data<bool>();
+  // check strings for valid float chars
+  thrust::transform(rmm::exec_policy(stream),
+                    thrust::make_counting_iterator<size_type>(0),
+                    thrust::make_counting_iterator<size_type>(strings.size()),
+                    d_results,
+                    [d_column] __device__(size_type idx) {
+                      if (d_column.is_null(idx)) return false;
+                      return string::is_float(d_column.element<string_view>(idx));
+                    });
+  results->set_null_count(strings.null_count());
+  return results;
+}
+
+}  // namespace detail
+
+// external API
+std::unique_ptr<column> is_float(strings_column_view const& strings,
+                                 rmm::mr::device_memory_resource* mr)
+{
+  CUDF_FUNC_RANGE();
+  return detail::is_float(strings, rmm::cuda_stream_default, mr);
+}
+
 }  // namespace strings
 }  // namespace cudf