Namespace for global string helper functions. More...

Constants
constexpr std::array	utfWhitespaces
	UTF-8 whitespaces used by utfTidy(). More...

constexpr auto	checkHexLength {3}
	Length of a two-digit hexademical number including the preceding percentage sign. More...

constexpr auto	randCharSet
	Characters to be chosen from for random string generation performed by generateRandom(). More...

Replacing
void	replaceAll (std::string &strInOut, std::string_view needle, std::string_view replacement)
	Replaces all occurences within a string with another string. More...

Conversion
bool	stringToBool (std::string inputString)
	Converts a string into a boolean value. More...

Number Format Checking
bool	isDec (std::string_view inputString)
	Checks whether a string contains only decimal digits and max. one dot (.). More...

bool	isHex (std::string_view inputString)
	Checks whether a string contains only hexadecimal digits. More...

Trimming
void	trim (std::string &stringToTrim)
	Removes whitespaces around a string. More...

Joining
std::string	join (const std::vector< std::string > &strings, char delimiter, bool ignoreEmpty)
	Concatenates all elements of a vector into a single string. More...

std::string	join (const std::vector< std::string > &strings, std::string_view delimiter, bool ignoreEmpty)
	Concatenates all elements of a vector into a single string. More...

std::string	join (std::queue< std::string > &strings, char delimiter, bool ignoreEmpty)
	Concatenates all elements of a queue into a single string. More...

std::string	join (std::queue< std::string > &strings, std::string_view delimiter, bool ignoreEmpty)
	Concatenates all elements of a queue into a single string. More...

void	join (const std::vector< std::string > &strings, char delimiter, bool ignoreEmpty, std::string &appendTo)
	Concatenates all elements of a vector and appends them to a string. More...

void	join (const std::vector< std::string > &strings, std::string_view delimiter, bool ignoreEmpty, std::string &appendTo)
	Concatenates all elements of a vector and appends them to a string. More...

void	join (std::queue< std::string > &strings, char delimiter, bool ignoreEmpty, std::string &appendTo)
	Concatenates all elements of a queue into a single string. More...

void	join (std::queue< std::string > &strings, std::string_view delimiter, bool ignoreEmpty, std::string &appendTo)
	Concatenates all elements of a queue into a single string. More...

Splitting
std::vector< std::string >	split (const std::string &str, char delimiter)
	Splits a string into a vector of strings using the given delimiter. More...

std::vector< std::string >	split (std::string_view str, std::string_view delimiter)
	Splits a string into a vector of strings using the given delimiter. More...

std::queue< std::string >	splitToQueue (std::string_view str, char delimiter, bool removeEmpty)
	Splits a string into a queue of strings using the given delimiter. More...

std::queue< std::string >	splitToQueue (std::string_view str, std::string_view delimiter, bool removeEmpty)
	Splits a string into a queue of strings using the given delimiter. More...

Sorting
void	sortAndRemoveDuplicates (std::vector< std::string > &vectorOfStrings, bool caseSensitive)
	Sorts the given vector of strings and removes duplicates. More...

Escape Characters
char	getFirstOrEscapeChar (std::string_view from)
	Gets the first character or an escaped character from the beginning of the given string. More...

Encoding
void	encodePercentage (std::string &stringToEncode)
	Encodes percentage signs that are not followed by a two-digit hexadecimal number with `%25`. More...

Tidying
void	utfTidy (std::string &stringToTidy)
	Removes new lines and unnecessary spaces, including UTF-8 whitespaces. More...

Name Checking
bool	checkDomainName (std::string_view name)
	Checks whether the given string is a a valid domain name. More...

bool	checkSQLName (std::string_view name)
	Checks whether the given string is a valid name for MySQL tables and fields. More...

Random String Generation
std::string	generateRandom (std::size_t length)
	Generates a random alpha-numerical string of the given length. More...

Detailed Description

Namespace for global string helper functions.

Function Documentation

◆ checkDomainName()

bool crawlservpp::Helper::Strings::checkDomainName ( std::string_view name )

inline

Checks whether the given string is a a valid domain name.

Note: Checks only for characters that would interfer with internal MySQL statements: /, \, and '.

Parameters

name	View of the string to be checked for a valid domain name.

Returns: True, if the string might be used as a domain name. False otherwise.

Referenced by crawlservpp::Main::Server::tick().

◆ checkSQLName()

bool crawlservpp::Helper::Strings::checkSQLName ( std::string_view name )

inline

Checks whether the given string is a valid name for MySQL tables and fields.

Parameters

name	View of the string to be checked for a valid MySQL table or field name.

Returns: True if the string might be used as a MySQL table or field name. False otherwise.

Referenced by crawlservpp::Main::Database::clearTable(), crawlservpp::Main::Database::isTargetTable(), crawlservpp::Module::Config::option(), crawlservpp::Main::Database::readColumnAsStrings(), crawlservpp::Main::Database::readTableAsStrings(), and crawlservpp::Main::Server::tick().

◆ encodePercentage()

void crawlservpp::Helper::Strings::encodePercentage ( std::string & stringToEncode )

inline

Encodes percentage signs that are not followed by a two-digit hexadecimal number with %25.

Parameters

stringToEncode Reference to the string in which the percentage signs will be encoded in-situ.

References checkHexLength, and isHex().

Referenced by crawlservpp::Parsing::URI::escapeUri().

◆ generateRandom()

std::string crawlservpp::Helper::Strings::generateRandom ( std::size_t length )

inline

Generates a random alpha-numerical string of the given length.

Parameters

length Length of the string to be generated.

Returns: The generated alpha-numerical string of the given length.

References randCharSet.

Referenced by crawlservpp::Main::WebServer::getIP(), and crawlservpp::Main::Server::tick().

◆ getFirstOrEscapeChar()

char crawlservpp::Helper::Strings::getFirstOrEscapeChar ( std::string_view from )

inline

Gets the first character or an escaped character from the beginning of the given string.

Escaped characters that are supported: \n, \t, and \\

Note: Only ASCII characters are supported. The returning character will be invalid, if the given string starts with a UTF-8 character.

Parameters

from	A view of the string to extract the character from.

Returns: the escaped character if the first two characters of the given string equal one of the supported escape sequences. The first character of the given string otherwise.

Referenced by crawlservpp::Module::Config::option().

◆ isDec()

bool crawlservpp::Helper::Strings::isDec ( std::string_view inputString )

inline

Checks whether a string contains only decimal digits and max. one dot (.).

Parameters

inputString A view into the string to check for decimal digits.

Returns: True, if the string only contains hexadecimal digits (0-9), max. one dot (.) and no whitespaces. False otherwise.

Referenced by crawlservpp::Data::ImportExport::OpenDocument::cell().

◆ isHex()

bool crawlservpp::Helper::Strings::isHex ( std::string_view inputString )

inline

Checks whether a string contains only hexadecimal digits.

Case-insensitive.

Parameters

inputString A view into the string to check for hexadecimal digits.

Returns: True, if the string only contains hexadecimal digits (0-F) and no whitespaces. False otherwise.

Referenced by encodePercentage().

◆ join() [1/8]

std::string crawlservpp::Helper::Strings::join	(	const std::vector< std::string > &	strings,
		char	delimiter,
		bool	ignoreEmpty
	)

inline

Concatenates all elements of a vector into a single string.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A character to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.

Returns: The string containing the concatenated elements, separated by the given delimiter, or an empty string if no elements have been concatenated.

Referenced by crawlservpp::Data::ImportExport::Text::exportList(), crawlservpp::Module::Parser::Thread::onReset(), and crawlservpp::Module::Extractor::Thread::onReset().

◆ join() [2/8]

std::string crawlservpp::Helper::Strings::join	(	const std::vector< std::string > &	strings,
		std::string_view	delimiter,
		bool	ignoreEmpty
	)

inline

Concatenates all elements of a vector into a single string.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	View of a string to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.

Returns: The string containing the concatenated elements, separated by the given delimiter, or an empty string if no elements have been concatenated.

◆ join() [3/8]

std::string crawlservpp::Helper::Strings::join	(	std::queue< std::string > &	strings,
		char	delimiter,
		bool	ignoreEmpty
	)

inline

Concatenates all elements of a queue into a single string.

Note: The queue will be completely emptied in the process, even if elements will be ignored.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A character to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.

Returns: The string containing the concatenated elements, separated by the given delimiter, or an empty string if no elements have been concatenated.

◆ join() [4/8]

std::string crawlservpp::Helper::Strings::join	(	std::queue< std::string > &	strings,
		std::string_view	delimiter,
		bool	ignoreEmpty
	)

inline

Concatenates all elements of a queue into a single string.

Note: The queue will be completely emptied in the process, even if elements will be ignored.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	View of a string to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.

Returns: The string containing the concatenated elements, separated by the given delimiter, or an empty string if no elements have been concatenated.

◆ join() [5/8]

void crawlservpp::Helper::Strings::join	(	const std::vector< std::string > &	strings,
		char	delimiter,
		bool	ignoreEmpty,
		std::string &	appendTo
	)

inline

Concatenates all elements of a vector and appends them to a string.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A character to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.
appendTo	The string that will be appended with the concatenated elements, separated by the given delimiter. It will remain unchanged, if no elements have been concatenated.

◆ join() [6/8]

void crawlservpp::Helper::Strings::join	(	const std::vector< std::string > &	strings,
		std::string_view	delimiter,
		bool	ignoreEmpty,
		std::string &	appendTo
	)

inline

Concatenates all elements of a vector and appends them to a string.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A view of the string to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.
appendTo	The string that will be appended with the concatenated elements, separated by the given delimiter. It will remain unchanged, if no elements have been concatenated.

◆ join() [7/8]

void crawlservpp::Helper::Strings::join	(	std::queue< std::string > &	strings,
		char	delimiter,
		bool	ignoreEmpty,
		std::string &	appendTo
	)

inline

Concatenates all elements of a queue into a single string.

Note: The queue will be completely emptied in the process, even if elements will be ignored.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A character to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.
appendTo	The string that will be appended with the concatenated elements, separated by the given delimiter. It will remain unchanged, if no elements have been concatenated.

◆ join() [8/8]

void crawlservpp::Helper::Strings::join	(	std::queue< std::string > &	strings,
		std::string_view	delimiter,
		bool	ignoreEmpty,
		std::string &	appendTo
	)

inline

Concatenates all elements of a queue into a single string.

Note: The queue will be completely emptied in the process, even if elements will be ignored.

Parameters

strings	Constant reference to a vector containing the strings to be concatenated.
delimiter	A view of the string to be inserted inbetween the concatenated strings.
ignoreEmpty	Ignore empty strings when concatenating the given elements.
appendTo	The string that will be appended with the concatenated elements, separated by the given delimiter. It will remain unchanged, if no elements have been concatenated.

◆ replaceAll()

void crawlservpp::Helper::Strings::replaceAll	(	std::string &	strInOut,
		std::string_view	needle,
		std::string_view	replacement
	)

inline

Replaces all occurences within a string with another string.

Note: No recursive replacement will be performed. Use a while loop for that.

Parameters

strInOut	A reference to the string in which the occurences will be replaced.
needle	A string view defining the occurence to be replaced.
replacement	A string view defining the replacement.

Referenced by crawlservpp::Data::ImportExport::OpenDocument::cell(), crawlservpp::Helper::DateTime::fixFinnishMonths(), crawlservpp::Helper::DateTime::fixFrenchMonths(), crawlservpp::Helper::DateTime::fixRussianMonths(), crawlservpp::Helper::DateTime::fixUkrainianMonths(), crawlservpp::Query::JsonPointer::getAll(), crawlservpp::Query::JsonPointer::getSubSets(), crawlservpp::Helper::DateTime::handle12hTime(), crawlservpp::Query::JsonPointer::JsonPointer(), crawlservpp::Module::Extractor::Thread::onReset(), crawlservpp::Module::Crawler::Thread::onReset(), crawlservpp::Helper::Json::parseCons(), crawlservpp::Helper::Json::parseRapid(), and utfTidy().

◆ sortAndRemoveDuplicates()

void crawlservpp::Helper::Strings::sortAndRemoveDuplicates	(	std::vector< std::string > &	vectorOfStrings,
		bool	caseSensitive
	)

inline

Sorts the given vector of strings and removes duplicates.

Note: Only ASCII characters are supported when sorting the string. Non-ASCII characters may result in a wrong sorting order.

Parameters

vectorOfStrings	Reference to the vector of strings, which will be sorted and from which duplicates will be removed in-situ.
caseSensitive	True, if the removal should be performed case-sensitive. False otherwise.

Referenced by crawlservpp::Module::Crawler::Thread::onReset().

◆ split() [1/2]

std::vector< std::string > crawlservpp::Helper::Strings::split	(	const std::string &	str,
		char	delimiter
	)

inline

Splits a string into a vector of strings using the given delimiter.

Parameters

str	A const reference to the string to be split up.
delimiter	The character around which the resulting elements will be splitted.

Returns: A new vector containing the splitted elements.

References split().

Referenced by crawlservpp::Data::Lemmatizer::clear(), crawlservpp::Main::Database::connect(), and crawlservpp::Helper::Portability::enumLocales().

◆ split() [2/2]

std::vector< std::string > crawlservpp::Helper::Strings::split	(	std::string_view	str,
		std::string_view	delimiter
	)

inline

Splits a string into a vector of strings using the given delimiter.

Parameters

str	A const reference to the string to be split up.
delimiter	A view of the string around which the resulting elements will be splitted.

Returns: A new vector containing the splitted elements.

Referenced by split(), and splitToQueue().

◆ splitToQueue() [1/2]

std::queue< std::string > crawlservpp::Helper::Strings::splitToQueue	(	std::string_view	str,
		char	delimiter,
		bool	removeEmpty
	)

inline

Splits a string into a queue of strings using the given delimiter.

Parameters

str	A const reference to the string to be split up.
delimiter	The character around which the resulting elements will be splitted.
removeEmpty	Set whether to ignore empty strings and not add them to the resulting queue.

Returns: A new queue containing the splitted elements.

References split().

Referenced by crawlservpp::Wrapper::TidyDoc::cleanAndRepair(), crawlservpp::Wrapper::TidyDoc::getOutput(), crawlservpp::Data::ImportExport::Text::importList(), and crawlservpp::Wrapper::TidyDoc::parse().

◆ splitToQueue() [2/2]

std::queue< std::string > crawlservpp::Helper::Strings::splitToQueue	(	std::string_view	str,
		std::string_view	delimiter,
		bool	removeEmpty
	)

inline

Splits a string into a queue of strings using the given delimiter.

Parameters

str	A const reference to the string to be split up.
delimiter	A view of the string around which the resulting elements will be splitted.
removeEmpty	Set whether to ignore empty strings and not add them to the resulting queue.

Returns: A new queue containing the splitted elements.

◆ stringToBool()

bool crawlservpp::Helper::Strings::stringToBool ( std::string inputString )

inline

Converts a string into a boolean value.

Only case-insensitive variations of "true" will be converted into true.

Note: In order for the conversion to be case-insensitive, a copy of the given string will be made.

Parameters

inputString The string to be converted into a boolean value.

Returns: True, if the given string represents true. False otherwise.

◆ trim()

void crawlservpp::Helper::Strings::trim ( std::string & stringToTrim )

inline

Removes whitespaces around a string.

Warning: Only ASCII whitespaces will be processed.

Parameters

stringToTrim Reference to the string to be trimmed in-situ.

See also: utfTidy

Referenced by crawlservpp::Main::Database::cloneTable(), crawlservpp::Main::Database::connect(), crawlservpp::Main::WebServer::getIP(), crawlservpp::Query::XPath::getSubSets(), crawlservpp::Query::JsonPath::JsonPath(), crawlservpp::Query::JsonPointer::JsonPointer(), crawlservpp::Module::Crawler::Thread::onReset(), crawlservpp::Module::Config::option(), crawlservpp::Parsing::URI::parseLink(), crawlservpp::Data::Stemmer::stemEnglish(), crawlservpp::Main::Server::tick(), and utfTidy().

◆ utfTidy()

void crawlservpp::Helper::Strings::utfTidy ( std::string & stringToTidy )

inline

Removes new lines and unnecessary spaces, including UTF-8 whitespaces.

Parameters

stringToTidy Reference to the string from which new lines and unnecessary spaces will be removed in-situ.

References replaceAll(), trim(), and utfWhitespaces.

Referenced by crawlservpp::Module::Parser::Thread::onReset(), and crawlservpp::Module::Extractor::Thread::onReset().

Variable Documentation

◆ checkHexLength

constexpr auto crawlservpp::Helper::Strings::checkHexLength {3}

inline

Length of a two-digit hexademical number including the preceding percentage sign.

Referenced by encodePercentage().

◆ randCharSet

constexpr auto crawlservpp::Helper::Strings::randCharSet

inline

Initial value:

{
        "01234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"sv
    }

Characters to be chosen from for random string generation performed by generateRandom().

Referenced by generateRandom().

◆ utfWhitespaces

constexpr std::array crawlservpp::Helper::Strings::utfWhitespaces

inline

Initial value:

{
        "\u0085"sv, 
        "\u00a0"sv, 
        "\u1680"sv, 
        "\u2000"sv, 
        "\u2001"sv, 
        "\u2002"sv, 
        "\u2003"sv, 
        "\u2004"sv, 
        "\u2005"sv, 
        "\u2006"sv, 
        "\u2007"sv, 
        "\u2008"sv, 
        "\u2009"sv, 
        "\u200a"sv, 
        "\u2028"sv, 
        "\u2029"sv, 
        "\u202f"sv, 
        "\u205f"sv, 
        "\u2060"sv, 
        "\u3000"sv, 
    }

UTF-8 whitespaces used by utfTidy().

Referenced by utfTidy().

Constants

Replacing

Conversion

Number Format Checking

Trimming

Joining

Splitting

Sorting

Escape Characters

Encoding

Tidying

Name Checking

Random String Generation

Detailed Description

Function Documentation

◆ checkDomainName()

◆ checkSQLName()

◆ encodePercentage()

◆ generateRandom()

◆ getFirstOrEscapeChar()

◆ isDec()

◆ isHex()

◆ join() [1/8]

◆ join() [2/8]

◆ join() [3/8]

◆ join() [4/8]

◆ join() [5/8]

◆ join() [6/8]

◆ join() [7/8]

◆ join() [8/8]

◆ replaceAll()

◆ sortAndRemoveDuplicates()

◆ split() [1/2]

◆ split() [2/2]

◆ splitToQueue() [1/2]

◆ splitToQueue() [2/2]

◆ stringToBool()

◆ trim()

◆ utfTidy()

Variable Documentation

◆ checkHexLength

◆ randCharSet

◆ utfWhitespaces