Modifying

Files
file	padding.hpp
file	strings/reverse.hpp
file	side_type.hpp
file	strip.hpp
file	translate.hpp
file	wrap.hpp

Enumerations
enum class	cudf::strings::side_type { cudf::strings::LEFT , cudf::strings::RIGHT , cudf::strings::BOTH }
	Direction identifier for cudf::strings::strip and cudf::strings::pad functions. More...
enum class	cudf::strings::filter_type : bool { cudf::strings::KEEP , cudf::strings::REMOVE }
	Removes or keeps the specified character ranges in cudf::strings::filter_characters. More...

Functions
std::unique_ptr< column >	cudf::strings::pad (strings_column_view const &input, size_type width, side_type side=side_type::RIGHT, std::string_view fill_char=" ", rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Add padding to each string using a provided character. More...
std::unique_ptr< column >	cudf::strings::zfill (strings_column_view const &input, size_type width, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Add '0' as padding to the left of each string. More...
std::unique_ptr< column >	cudf::strings::reverse (strings_column_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Reverses the characters within each string. More...
std::unique_ptr< column >	cudf::strings::strip (strings_column_view const &input, side_type side=side_type::BOTH, string_scalar const &to_strip=string_scalar(""), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Removes the specified characters from the beginning or end (or both) of each string. More...
std::unique_ptr< column >	cudf::strings::translate (strings_column_view const &input, std::vector< std::pair< char_utf8, char_utf8 >> const &chars_table, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Translates individual characters within each string. More...
std::unique_ptr< column >	cudf::strings::filter_characters (strings_column_view const &input, std::vector< std::pair< cudf::char_utf8, cudf::char_utf8 >> characters_to_filter, filter_type keep_characters=filter_type::KEEP, string_scalar const &replacement=string_scalar(""), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Removes ranges of characters from each string in a strings column. More...
std::unique_ptr< column >	cudf::strings::wrap (strings_column_view const &input, size_type width, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Wraps strings onto multiple lines shorter than width by replacing appropriate white space with new-line characters (ASCII 0x0A). More...

Detailed Description

Enumeration Type Documentation

filter_type

enum cudf::strings::filter_type : bool

strong

Removes or keeps the specified character ranges in cudf::strings::filter_characters.

Enumerator
KEEP	All characters but those specified are removed.
REMOVE	Only the specified characters are removed.

Definition at line 66 of file translate.hpp.

side_type

enum cudf::strings::side_type

strong

Direction identifier for cudf::strings::strip and cudf::strings::pad functions.

Enumerator
LEFT	strip/pad characters from the beginning of the string
RIGHT	strip/pad characters from the end of the string
BOTH	strip/pad characters from the beginning and end of the string

Definition at line 31 of file side_type.hpp.

Function Documentation

filter_characters()

std::unique_ptr<column> cudf::strings::filter_characters	(	strings_column_view const &	input,
		std::vector< std::pair< cudf::char_utf8, cudf::char_utf8 >>	characters_to_filter,
		filter_type	keep_characters = filter_type::KEEP,
		string_scalar const &	replacement = string_scalar(""),
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Removes ranges of characters from each string in a strings column.

This can also be used to keep only the specified character ranges and remove all others from each string.

Example:
s = ["aeiou", "AEIOU", "0123456789", "bcdOPQ5"]
f = [{'M','Z'}, {'a','l'}, {'4','6'}]
r1 = filter_characters(s, f)
r1 is now ["aei", "OU", "456", "bcdOPQ5"]
r2 = filter_characters(s, f, REMOVE)
r2 is now ["ou", "AEI", "0123789", ""]
r3 = filter_characters(s, f, KEEP, "*")
r3 is now ["aei**", "***OU", "****456***", "bcdOPQ5"]

Null string entries result in null entries in the output column.

Exceptions

cudf::logic_error

if replacement is invalid

Parameters

input	Strings instance for this operation
characters_to_filter	Table of character ranges to filter on
keep_characters	If true, the characters_to_filter are retained and all other characters are removed
replacement	Optional replacement string for each character removed
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 with filtered strings

pad()

std::unique_ptr<column> cudf::strings::pad	(	strings_column_view const &	input,
		size_type	width,
		side_type	side = side_type::RIGHT,
		std::string_view	fill_char = " ",
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Add padding to each string using a provided character.

If the string is already width or more characters, no padding is performed. Also, no strings are truncated.

Null string entries result in corresponding null entries in the output column.

Example:
s = ['aa','bbb','cccc','ddddd']
r = pad(s,4)
r is now ['aa  ','bbb ','cccc','ddddd']

Parameters

input	Strings instance for this operation
width	The minimum number of characters for each string
side	Where to place the padding characters; Default is pad right (left justify)
fill_char	Single UTF-8 character to use for padding; Default is the space 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 column with padded strings

reverse()

std::unique_ptr<column> cudf::strings::reverse	(	strings_column_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Reverses the characters within each string.

Any null string entries return corresponding null output column entries.

Example:
s = ["abcdef", "12345", "", "A"]
r = reverse(s)
r is now ["fedcba", "54321", "", "A"]

Parameters

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

Returns

New strings column

strip()

std::unique_ptr<column> cudf::strings::strip	(	strings_column_view const &	input,
		side_type	side = side_type::BOTH,
		string_scalar const &	to_strip = string_scalar(""),
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Removes the specified characters from the beginning or end (or both) of each string.

The to_strip parameter can contain one or more characters. All characters in to_strip are removed from the input strings.

If to_strip is the empty string, whitespace characters are removed. Whitespace is considered the space character plus control characters like tab and line feed.

Any null string entries return corresponding null output column entries.

Example:
s = [" aaa ", "_bbbb ", "__cccc  ", "ddd", " ee _ff gg_"]
r = strip(s,both," _")
r is now ["aaa", "bbbb", "cccc", "ddd", "ee _ff gg"]

Exceptions

cudf::logic_error

if to_strip is invalid.

Parameters

input	Strings column for this operation
side	Indicates characters are to be stripped from the beginning, end, or both of each string; Default is both
to_strip	UTF-8 encoded characters to strip from each string; Default is empty string which indicates strip whitespace characters
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 strings column.

translate()

std::unique_ptr<column> cudf::strings::translate	(	strings_column_view const &	input,
		std::vector< std::pair< char_utf8, char_utf8 >> const &	chars_table,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Translates individual characters within each string.

This can also be used to remove a character by specifying 0 for the corresponding table entry.

Null string entries result in null entries in the output column.

Example:
s = ["aa","bbb","cccc","abcd"]
t = [['a','A'],['b',''],['d':'Q']]
r = translate(s,t)
r is now ["AA", "", "cccc", "AcQ"]

Parameters

input	Strings instance for this operation
chars_table	Table of UTF-8 character mappings
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 with padded strings

wrap()

std::unique_ptr<column> cudf::strings::wrap	(	strings_column_view const &	input,
		size_type	width,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Wraps strings onto multiple lines shorter than width by replacing appropriate white space with new-line characters (ASCII 0x0A).

For each string row in the input column longer than width, the corresponding output string row will have newline characters inserted so that each line is no more than width characters. Attempts to use existing white space locations to split the strings, but may split non-white-space sequences if necessary.

Any null string entries return corresponding null output column entries.

Example 1:

width = 3
input_string_tbl = [ "12345", "thesé", nullptr, "ARE THE", "tést strings", "" ];
 
wrapped_string_tbl = wrap(input_string_tbl, width)
wrapped_string_tbl = [ "12345", "thesé", nullptr, "ARE\nTHE", "tést\nstrings", "" ]

Example 2:

width = 12;
input_string_tbl = ["the quick brown fox jumped over the lazy brown dog", "hello, world"]
 
wrapped_string_tbl = wrap(input_string_tbl, width)
wrapped_string_tbl = ["the quick\nbrown fox\njumped over\nthe lazy\nbrown dog", "hello, world"]

Parameters

input	String column
width	Maximum character width of a line within each string
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

Column of wrapped strings

zfill()

std::unique_ptr<column> cudf::strings::zfill	(	strings_column_view const &	input,
		size_type	width,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Add '0' as padding to the left of each string.

This is equivalent to ‘pad(width,left,'0’)` but preserves the sign character if it appears in the first position.

If the string is already width or more characters, no padding is performed. No strings are truncated.

Null rows in the input result in corresponding null rows in the output column.

Example:
s = ['1234','-9876','+0.34','-342567', '2+2']
r = zfill(s,6)
r is now ['001234','-09876','+00.34','-342567', '0002+2']

Parameters

input	Strings instance for this operation
width	The minimum number of characters for each string
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 strings