Remove deprecated regex functions from libcudf

cpp/include/cudf/strings/contains.hpp

@@ -60,36 +60,6 @@ std::unique_ptr<column> contains_re(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a boolean column identifying rows which
- * match the given regex pattern.
- *
- * @code{.pseudo}
- * Example:
- * s = ["abc","123","def456"]
- * r = contains_re(s,"\\d+")
- * r is now [false, true, true]
- * @endcode
- *
- * Any null string entries return corresponding null output column entries.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link contains_re contains_re(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern Regex pattern to match to each string.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New column of boolean results for each string.
- */
-[[deprecated]] std::unique_ptr<column> contains_re(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /**
  * @brief Returns a boolean column identifying rows which
  * matching the given regex_program object but only at the beginning the string.
@@ -116,36 +86,6 @@ std::unique_ptr<column> matches_re(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a boolean column identifying rows which
- * matching the given regex pattern but only at the beginning the string.
- *
- * @code{.pseudo}
- * Example:
- * s = ["abc","123","def456"]
- * r = matches_re(s,"\\d+")
- * r is now [false, true, false]
- * @endcode
- *
- * Any null string entries return corresponding null output column entries.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link matches_re matches_re(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern Regex pattern to match to each string.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New column of boolean results for each string.
- */
-[[deprecated]] std::unique_ptr<column> matches_re(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /**
  * @brief Returns the number of times the given regex_program's pattern
  * matches in each string
@@ -172,36 +112,6 @@ std::unique_ptr<column> count_re(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns the number of times the given regex pattern
- * matches in each string.
- *
- * @code{.pseudo}
- * Example:
- * s = ["abc","123","def45"]
- * r = count_re(s,"\\d")
- * r is now [0, 3, 2]
- * @endcode
- *
- * Any null string entries return corresponding null output column entries.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link count_re count_re(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern Regex pattern to match within each string.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New INT32 column with counts for each string.
- */
-[[deprecated]] std::unique_ptr<column> count_re(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /**
  * @brief Returns a boolean column identifying rows which
  * match the given like pattern.

cpp/include/cudf/strings/extract.hpp

@@ -63,41 +63,6 @@ std::unique_ptr<table> extract(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a table of strings columns where each column corresponds to the matching
- * group specified in the given regular expression pattern.
- *
- * All the strings for the first group will go in the first output column; the second group
- * go in the second column and so on. Null entries are added to the columns in row `i` if
- * the string at row `i` does not match.
- *
- * Any null string entries return corresponding null output column entries.
- *
- * @code{.pseudo}
- * Example:
- * s = ["a1", "b2", "c3"]
- * r = extract(s, "([ab])(\\d)")
- * r is now [ ["a", "b", null],
- *            ["1", "2", null] ]
- * @endcode
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link extract extract(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern The regular expression pattern with group indicators.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned table's device memory.
- * @return Columns of strings extracted from the input column.
- */
-[[deprecated]] std::unique_ptr<table> extract(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /**
  * @brief Returns a lists column of strings where each string column row corresponds to the
  * matching group specified in the given regex_program object
@@ -132,44 +97,6 @@ std::unique_ptr<column> extract_all_record(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a lists column of strings where each string column row corresponds to the
- * matching group specified in the given regular expression pattern.
- *
- * All the matching groups for the first row will go in the first row output column; the second
- * row results will go into the second row output column and so on.
- *
- * A null output row will result if the corresponding input string row does not match or
- * that input row is null.
- *
- * @code{.pseudo}
- * Example:
- * s = ["a1 b4", "b2", "c3 a5", "b", null]
- * r = extract_all_record(s,"([ab])(\\d)")
- * r is now [ ["a", "1", "b", "4"],
- *            ["b", "2"],
- *            ["a", "5"],
- *            null,
- *            null ]
- * @endcode
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link extract_all_record extract_all_record(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern The regular expression pattern with group indicators.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate any returned device memory.
- * @return Lists column containing strings extracted from the input column.
- */
-[[deprecated]] std::unique_ptr<column> extract_all_record(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /** @} */  // end of doxygen group
 }  // namespace strings
 }  // namespace cudf

cpp/include/cudf/strings/findall.hpp

@@ -65,43 +65,6 @@ std::unique_ptr<column> findall(
   regex_program const& prog,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief Returns a lists column of strings for each matching occurrence of the
- * regex pattern within each string.
- *
- * Each output row includes all the substrings within the corresponding input row
- * that match the given pattern. If no matches are found, the output row is empty.
- *
- * @code{.pseudo}
- * Example:
- * s = ["bunny", "rabbit", "hare", "dog"]
- * r = findall(s, "[ab]")
- * r is now a lists column like:
- *  [ ["b"]
- *    ["a","b","b"]
- *    ["a"]
- *    [] ]
- * @endcode
- *
- * A null output row occurs if the corresponding input row is null.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link findall findall(strings_column_view const&,
- * regex_program const&, rmm::mr::device_memory_resource*) @endlink
- *
- * @param input Strings instance for this operation.
- * @param pattern Regex pattern to match within each string.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New lists column of strings.
- */
-[[deprecated]] std::unique_ptr<column> findall(
-  strings_column_view const& input,
-  std::string_view pattern,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 /** @} */  // end of doxygen group
 }  // namespace strings
 }  // namespace cudf

cpp/include/cudf/strings/replace_re.hpp

@@ -59,35 +59,6 @@ std::unique_ptr<column> replace_re(
   std::optional<size_type> max_replace_count = std::nullopt,
   rmm::mr::device_memory_resource* mr        = rmm::mr::get_current_device_resource());
 
-/**
- * @brief For each string, replaces any character sequence matching the given pattern
- * with the provided replacement string.
- *
- * Any null string entries return corresponding null output column entries.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link replace_re replace_re(strings_column_view const&, regex_program const&,
- * string_scalar const&, std::optional<size_type>, rmm::mr::device_memory_resource*) @endlink
- *
- * @param strings Strings instance for this operation.
- * @param pattern The regular expression pattern to search within each string.
- * @param replacement The string used to replace the matched sequence in each string.
- *        Default is an empty string.
- * @param max_replace_count The maximum number of times to replace the matched pattern
- *        within each string. Default replaces every substring that is matched.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New strings column.
- */
-[[deprecated]] std::unique_ptr<column> replace_re(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  string_scalar const& replacement           = string_scalar(""),
-  std::optional<size_type> max_replace_count = std::nullopt,
-  regex_flags const flags                    = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr        = rmm::mr::get_current_device_resource());
-
 /**
  * @brief For each string, replaces any character sequence matching the given patterns
  * with the corresponding string in the `replacements` column.
@@ -133,33 +104,5 @@ std::unique_ptr<column> replace_with_backrefs(
   std::string_view replacement,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-/**
- * @brief For each string, replaces any character sequence matching the given pattern
- * using the replacement template for back-references.
- *
- * Any null string entries return corresponding null output column entries.
- *
- * See the @ref md_regex "Regex Features" page for details on patterns supported by this API.
- *
- * @deprecated Use @link replace_with_backrefs replace_with_backrefs(strings_column_view const&,
- * regex_program const&, string_view, rmm::mr::device_memory_resource*) @endlink
- *
- * @throw cudf::logic_error if capture index values in `replacement` are not in range 0-99, and also
- * if the index exceeds the group count specified in the pattern
- *
- * @param strings Strings instance for this operation.
- * @param pattern The regular expression patterns to search within each string.
- * @param replacement The replacement template for creating the output string.
- * @param flags Regex flags for interpreting special characters in the pattern.
- * @param mr Device memory resource used to allocate the returned column's device memory.
- * @return New strings column.
- */
-[[deprecated]] std::unique_ptr<column> replace_with_backrefs(
-  strings_column_view const& strings,
-  std::string_view pattern,
-  std::string_view replacement,
-  regex_flags const flags             = regex_flags::DEFAULT,
-  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
-
 }  // namespace strings
 }  // namespace cudf