Remove default parameters for nvtext::detail functions (#12007)

Removes default parameters from the `nvtext::detail` functions. Most of these were internal default parameters which were unnecessary. The nvtext detail functions are only used within nvtext APIs.

Reference #11967

Authors:
  - David Wendt (https://github.com/davidwendt)

Approvers:
  - Bradley Dice (https://github.com/bdice)
  - Nghia Truong (https://github.com/ttnghia)

URL: #12007

cpp/include/nvtext/detail/tokenize.hpp

@@ -35,12 +35,10 @@ namespace detail {
  * @param mr Device memory resource used to allocate the returned column's device memory.
  * @return New strings columns of tokens.
  */
-std::unique_ptr<cudf::column> tokenize(
-  cudf::strings_column_view const& strings,
-  cudf::string_scalar const& delimiter = cudf::string_scalar{""},
-  // Move before delimiter?
-  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+std::unique_ptr<cudf::column> tokenize(cudf::strings_column_view const& strings,
+                                       cudf::string_scalar const& delimiter,
+                                       rmm::cuda_stream_view stream,
+                                       rmm::mr::device_memory_resource* mr);
 
 /**
  * @copydoc nvtext::tokenize(strings_column_view const&,strings_column_view
@@ -52,11 +50,10 @@ std::unique_ptr<cudf::column> tokenize(
  * @param mr Device memory resource used to allocate the returned column's device memory.
  * @return New strings columns of tokens.
  */
-std::unique_ptr<cudf::column> tokenize(
-  cudf::strings_column_view const& strings,
-  cudf::strings_column_view const& delimiters,
-  rmm::cuda_stream_view stream,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+std::unique_ptr<cudf::column> tokenize(cudf::strings_column_view const& strings,
+                                       cudf::strings_column_view const& delimiters,
+                                       rmm::cuda_stream_view stream,
+                                       rmm::mr::device_memory_resource* mr);
 
 /**
  * @copydoc nvtext::count_tokens(strings_column_view const&, string_scalar
@@ -69,12 +66,10 @@ std::unique_ptr<cudf::column> tokenize(
  * @param mr Device memory resource used to allocate the returned column's device memory.
  * @return New INT32 column of token counts.
  */
-std::unique_ptr<cudf::column> count_tokens(
-  cudf::strings_column_view const& strings,
-  cudf::string_scalar const& delimiter = cudf::string_scalar{""},
-  // Move before delimiter?
-  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+std::unique_ptr<cudf::column> count_tokens(cudf::strings_column_view const& strings,
+                                           cudf::string_scalar const& delimiter,
+                                           rmm::cuda_stream_view stream,
+                                           rmm::mr::device_memory_resource* mr);
 
 /**
  * @copydoc nvtext::count_tokens(strings_column_view const&,strings_column_view
@@ -86,11 +81,10 @@ std::unique_ptr<cudf::column> count_tokens(
  * @param mr Device memory resource used to allocate the returned column's device memory.
  * @return New INT32 column of token counts.
  */
-std::unique_ptr<cudf::column> count_tokens(
-  cudf::strings_column_view const& strings,
-  cudf::strings_column_view const& delimiters,
-  rmm::cuda_stream_view stream,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
+std::unique_ptr<cudf::column> count_tokens(cudf::strings_column_view const& strings,
+                                           cudf::strings_column_view const& delimiters,
+                                           rmm::cuda_stream_view stream,
+                                           rmm::mr::device_memory_resource* mr);
 
 }  // namespace detail
 }  // namespace nvtext

cpp/src/text/generate_ngrams.cu

@@ -84,12 +84,11 @@ struct ngram_generator_fn {
 
 }  // namespace
 
-std::unique_ptr<cudf::column> generate_ngrams(
-  cudf::strings_column_view const& strings,
-  cudf::size_type ngrams               = 2,
-  cudf::string_scalar const& separator = cudf::string_scalar{"_"},
-  rmm::cuda_stream_view stream         = cudf::get_default_stream(),
-  rmm::mr::device_memory_resource* mr  = rmm::mr::get_current_device_resource())
+std::unique_ptr<cudf::column> generate_ngrams(cudf::strings_column_view const& strings,
+                                              cudf::size_type ngrams,
+                                              cudf::string_scalar const& separator,
+                                              rmm::cuda_stream_view stream,
+                                              rmm::mr::device_memory_resource* mr)
 {
   CUDF_EXPECTS(separator.is_valid(stream), "Parameter separator must be valid");
   cudf::string_view const d_separator(separator.data(), separator.size());

cpp/src/text/ngrams_tokenize.cu

@@ -134,13 +134,12 @@ struct ngram_builder_fn {
 
 // detail APIs
 
-std::unique_ptr<cudf::column> ngrams_tokenize(
-  cudf::strings_column_view const& strings,
-  cudf::size_type ngrams               = 2,
-  cudf::string_scalar const& delimiter = cudf::string_scalar(""),
-  cudf::string_scalar const& separator = cudf::string_scalar{"_"},
-  rmm::cuda_stream_view stream         = cudf::get_default_stream(),
-  rmm::mr::device_memory_resource* mr  = rmm::mr::get_current_device_resource())
+std::unique_ptr<cudf::column> ngrams_tokenize(cudf::strings_column_view const& strings,
+                                              cudf::size_type ngrams,
+                                              cudf::string_scalar const& delimiter,
+                                              cudf::string_scalar const& separator,
+                                              rmm::cuda_stream_view stream,
+                                              rmm::mr::device_memory_resource* mr)
 {
   CUDF_EXPECTS(delimiter.is_valid(stream), "Parameter delimiter must be valid");
   cudf::string_view d_delimiter(delimiter.data(), delimiter.size());

cpp/src/text/normalize.cu

@@ -170,10 +170,9 @@ struct codepoint_to_utf8_fn {
 }  // namespace
 
 // detail API
-std::unique_ptr<cudf::column> normalize_spaces(
-  cudf::strings_column_view const& strings,
-  rmm::cuda_stream_view stream,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource())
+std::unique_ptr<cudf::column> normalize_spaces(cudf::strings_column_view const& strings,
+                                               rmm::cuda_stream_view stream,
+                                               rmm::mr::device_memory_resource* mr)
 {
   if (strings.is_empty()) return cudf::make_empty_column(cudf::data_type{cudf::type_id::STRING});