Files
file	strings/contains.hpp
	Strings APIs for regex contains, count, matches, like.

file	findall.hpp

Functions
std::unique_ptr< column >	cudf::strings::contains_re (strings_column_view const &input, regex_program const &prog, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns a boolean column identifying rows which match the given regex_program object. More...

std::unique_ptr< column >	cudf::strings::matches_re (strings_column_view const &input, regex_program const &prog, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns a boolean column identifying rows which matching the given regex_program object but only at the beginning the string. More...

std::unique_ptr< column >	cudf::strings::count_re (strings_column_view const &input, regex_program const &prog, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns the number of times the given regex_program's pattern matches in each string. More...

std::unique_ptr< column >	cudf::strings::like (strings_column_view const &input, string_scalar const &pattern, string_scalar const &escape_character=string_scalar(""), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns a boolean column identifying rows which match the given like pattern. More...

std::unique_ptr< column >	cudf::strings::like (strings_column_view const &input, strings_column_view const &patterns, string_scalar const &escape_character=string_scalar(""), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns a boolean column identifying rows which match the corresponding like pattern in the given patterns. More...

std::unique_ptr< column >	cudf::strings::findall (strings_column_view const &input, regex_program const &prog, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
	Returns a lists column of strings for each matching occurrence using the regex_program pattern within each string. More...

Detailed Description

Function Documentation

◆ contains_re()

std::unique_ptr<column> cudf::strings::contains_re	(	strings_column_view const &	input,
		regex_program const &	prog,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns a boolean column identifying rows which match the given regex_program object.

Example:
s = ["abc", "123", "def456"]
p = regex_program::create("\\d+")
r = contains_re(s, p)
r is now [false, true, true]

Any null string entries return corresponding null output column entries.

See the Regex Features page for details on patterns supported by this API.

Parameters

input	Strings instance for this operation
prog	Regex program instance
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New column of boolean results for each string

◆ count_re()

std::unique_ptr<column> cudf::strings::count_re	(	strings_column_view const &	input,
		regex_program const &	prog,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns the number of times the given regex_program's pattern matches in each string.

Example:
s = ["abc", "123", "def45"]
p = regex_program::create("\\d")
r = count_re(s, p)
r is now [0, 3, 2]

Any null string entries return corresponding null output column entries.

See the Regex Features page for details on patterns supported by this API.

Parameters

input	Strings instance for this operation
prog	Regex program instance
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New column of match counts for each string

◆ findall()

std::unique_ptr<column> cudf::strings::findall	(	strings_column_view const &	input,
		regex_program const &	prog,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns a lists column of strings for each matching occurrence using the regex_program 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.

Example:
s = ["bunny", "rabbit", "hare", "dog"]
p = regex_program::create("[ab]")
r = findall(s, p)
r is now a lists column like:
 [ ["b"]
   ["a","b","b"]
   ["a"]
   [] ]

A null output row occurs if the corresponding input row is null.

See the Regex Features page for details on patterns supported by this API.

Parameters

input	Strings instance for this operation
prog	Regex program instance
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New lists column of strings

◆ like() [1/2]

std::unique_ptr<column> cudf::strings::like	(	strings_column_view const &	input,
		string_scalar const &	pattern,
		string_scalar const &	escape_character = `string_scalar("")`,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns a boolean column identifying rows which match the given like pattern.

The like pattern expects only 2 wildcard special characters:

% zero or more of any character
_ any single character

Example:
s = ["azaa", "ababaabba", "aaxa"]
r = like(s, "%a_aa%")
r is now [1, 1, 0]
r = like(s, "a__a")
r is now [1, 0, 1]

Specify an escape character to include either % or _ in the search. The escape_character is expected to be either 0 or 1 characters. If more than one character is specified only the first character is used.

Example:
s = ["abc_def", "abc1def", "abc_"]
r = like(s, "abc/_d%", "/")
r is now [1, 0, 0]

Any null string entries return corresponding null output column entries.

Exceptions

cudf::logic_error if pattern or escape_character is invalid

Parameters

input	Strings instance for this operation
pattern	Like pattern to match within each string
escape_character	Optional character specifies the escape prefix. Default is no escape character.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New boolean column

◆ like() [2/2]

std::unique_ptr<column> cudf::strings::like	(	strings_column_view const &	input,
		strings_column_view const &	patterns,
		string_scalar const &	escape_character = `string_scalar("")`,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns a boolean column identifying rows which match the corresponding like pattern in the given patterns.

The like pattern expects only 2 wildcard special characters:

% zero or more of any character
_ any single character

Example:
s = ["azaa", "ababaabba", "aaxa"]
p = ["%a", "b%", "__x_"]
r = like(s, p)
r is now [1, 0, 1]

Specify an escape character to include either % or _ in the search. The escape_character is expected to be either 0 or 1 characters. If more than one character is specified only the first character is used. The escape character is applied to all patterns.

Any null string entries return corresponding null output column entries.

Exceptions

cudf::logic_error	if `patterns` contains nulls or `escape_character` is invalid
cudf::logic_error	if `patterns.size() != input.size()`

Parameters

input	Strings instance for this operation
patterns	Like patterns to match within each corresponding string
escape_character	Optional character specifies the escape prefix. Default is no escape character.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New boolean column

◆ matches_re()

std::unique_ptr<column> cudf::strings::matches_re	(	strings_column_view const &	input,
		regex_program const &	prog,
		rmm::cuda_stream_view	stream = `cudf::get_default_stream()`,
		rmm::mr::device_memory_resource *	mr = `rmm::mr::get_current_device_resource()`
	)

Returns a boolean column identifying rows which matching the given regex_program object but only at the beginning the string.

Example:
s = ["abc", "123", "def456"]
p = regex_program::create("\\d+")
r = matches_re(s, p)
r is now [false, true, false]

Any null string entries return corresponding null output column entries.

See the Regex Features page for details on patterns supported by this API.

Parameters

input	Strings instance for this operation
prog	Regex program instance
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns: New column of boolean results for each string

Files

Functions

Detailed Description

Function Documentation

◆ contains_re()

◆ count_re()

◆ findall()

◆ like() [1/2]

◆ like() [2/2]

◆ matches_re()