CharPointer_UTF8 Class Reference

Wraps a pointer to a null-terminated UTF-8 character string, and provides various methods to operate on the data. More...

#include <juce_CharPointer_UTF8.h>

Public Types
enum	{ byteOrderMark1 = 0xef , byteOrderMark2 = 0xbb , byteOrderMark3 = 0xbf }
	These values are the byte-order mark (BOM) values for a UTF-8 stream. More...
using	CharType = char

Public Member Functions
	CharPointer_UTF8 (const CharType *rawPointer) noexcept
	CharPointer_UTF8 (const CharPointer_UTF8 &other)=default
CharPointer_UTF8 &	operator= (const CharPointer_UTF8 &other) noexcept=default
CharPointer_UTF8 &	operator= (const CharType *text) noexcept
bool	operator== (CharPointer_UTF8 other) const noexcept
	This is a pointer comparison, it doesn't compare the actual text.
bool	operator!= (CharPointer_UTF8 other) const noexcept
bool	operator<= (CharPointer_UTF8 other) const noexcept
bool	operator< (CharPointer_UTF8 other) const noexcept
bool	operator>= (CharPointer_UTF8 other) const noexcept
bool	operator> (CharPointer_UTF8 other) const noexcept
CharType *	getAddress () const noexcept
	Returns the address that this pointer is pointing to.
	operator const CharType * () const noexcept
	Returns the address that this pointer is pointing to.
bool	isEmpty () const noexcept
	Returns true if this pointer is pointing to a null character.
bool	isNotEmpty () const noexcept
	Returns true if this pointer is not pointing to a null character.
juce_wchar	operator* () const noexcept
	Returns the unicode character that this pointer is pointing to.
CharPointer_UTF8 &	operator++ () noexcept
	Moves this pointer along to the next character in the string.
CharPointer_UTF8 &	operator-- () noexcept
	Moves this pointer back to the previous character in the string.
juce_wchar	getAndAdvance () noexcept
	Returns the character that this pointer is currently pointing to, and then advances the pointer to point to the next character.
CharPointer_UTF8	operator++ (int) noexcept
	Moves this pointer along to the next character in the string.
CharPointer_UTF8 &	operator+= (int numToSkip) noexcept
	Moves this pointer forwards by the specified number of characters.
CharPointer_UTF8 &	operator-= (int numToSkip) noexcept
	Moves this pointer backwards by the specified number of characters.
juce_wchar	operator[] (int characterIndex) const noexcept
	Returns the character at a given character index from the start of the string.
CharPointer_UTF8	operator+ (int numToSkip) const noexcept
	Returns a pointer which is moved forwards from this one by the specified number of characters.
CharPointer_UTF8	operator- (int numToSkip) const noexcept
	Returns a pointer which is moved backwards from this one by the specified number of characters.
size_t	length () const noexcept
	Returns the number of characters in this string.
size_t	lengthUpTo (const size_t maxCharsToCount) const noexcept
	Returns the number of characters in this string, or the given value, whichever is lower.
size_t	lengthUpTo (const CharPointer_UTF8 end) const noexcept
	Returns the number of characters in this string, or up to the given end pointer, whichever is lower.
size_t	sizeInBytes () const noexcept
	Returns the number of bytes that are used to represent this string.
CharPointer_UTF8	findTerminatingNull () const noexcept
	Returns a pointer to the null character that terminates this string.
void	write (const juce_wchar charToWrite) noexcept
	Writes a unicode character to this string, and advances this pointer to point to the next position.
void	writeNull () const noexcept
	Writes a null character to this string (leaving the pointer's position unchanged).
template<typename CharPointer >
void	writeAll (const CharPointer src) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes.
void	writeAll (const CharPointer_UTF8 src) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes.
template<typename CharPointer >
size_t	writeWithDestByteLimit (const CharPointer src, const size_t maxDestBytes) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes.
template<typename CharPointer >
void	writeWithCharLimit (const CharPointer src, const int maxChars) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes.
template<typename CharPointer >
int	compare (const CharPointer other) const noexcept
	Compares this string with another one.
template<typename CharPointer >
int	compareUpTo (const CharPointer other, const int maxChars) const noexcept
	Compares this string with another one, up to a specified number of characters.
template<typename CharPointer >
int	compareIgnoreCase (const CharPointer other) const noexcept
	Compares this string with another one.
int	compareIgnoreCase (const CharPointer_UTF8 other) const noexcept
	Compares this string with another one.
template<typename CharPointer >
int	compareIgnoreCaseUpTo (const CharPointer other, const int maxChars) const noexcept
	Compares this string with another one, up to a specified number of characters.
template<typename CharPointer >
int	indexOf (const CharPointer stringToFind) const noexcept
	Returns the character index of a substring, or -1 if it isn't found.
int	indexOf (const juce_wchar charToFind) const noexcept
	Returns the character index of a unicode character, or -1 if it isn't found.
int	indexOf (const juce_wchar charToFind, const bool ignoreCase) const noexcept
	Returns the character index of a unicode character, or -1 if it isn't found.
bool	isWhitespace () const noexcept
	Returns true if the first character of this string is whitespace.
bool	isDigit () const noexcept
	Returns true if the first character of this string is a digit.
bool	isLetter () const noexcept
	Returns true if the first character of this string is a letter.
bool	isLetterOrDigit () const noexcept
	Returns true if the first character of this string is a letter or digit.
bool	isUpperCase () const noexcept
	Returns true if the first character of this string is upper-case.
bool	isLowerCase () const noexcept
	Returns true if the first character of this string is lower-case.
juce_wchar	toUpperCase () const noexcept
	Returns an upper-case version of the first character of this string.
juce_wchar	toLowerCase () const noexcept
	Returns a lower-case version of the first character of this string.
int	getIntValue32 () const noexcept
	Parses this string as a 32-bit integer.
int64	getIntValue64 () const noexcept
	Parses this string as a 64-bit integer.
double	getDoubleValue () const noexcept
	Parses this string as a floating point double.
CharPointer_UTF8	findEndOfWhitespace () const noexcept
	Returns the first non-whitespace character in the string.
void	incrementToEndOfWhitespace () noexcept
	Move this pointer to the first non-whitespace character in the string.
CharPointer_UTF8	atomicSwap (const CharPointer_UTF8 newValue)
	Atomically swaps this pointer for a new value, returning the previous value.

Static Public Member Functions
static size_t	getBytesRequiredFor (const juce_wchar charToWrite) noexcept
	Returns the number of bytes that would be needed to represent the given unicode character in this encoding format.
template<class CharPointer >
static size_t	getBytesRequiredFor (CharPointer text) noexcept
	Returns the number of bytes that would be needed to represent the given string in this encoding format.
static bool	canRepresent (juce_wchar character) noexcept
	Returns true if the given unicode character can be represented in this encoding.
static bool	isValidString (const CharType *codeUnits, int maxBytesToRead)
	Returns true if this data contains a valid string in this encoding.
static bool	isByteOrderMark (const void *possibleByteOrder) noexcept
	Returns true if the first three bytes in this pointer are the UTF8 byte-order mark (BOM).

Detailed Description

Wraps a pointer to a null-terminated UTF-8 character string, and provides various methods to operate on the data.

See also

CharPointer_UTF16, CharPointer_UTF32

Member Typedef Documentation

CharType

using CharPointer_UTF8::CharType = char

Member Enumeration Documentation

anonymous enum

anonymous enum

These values are the byte-order mark (BOM) values for a UTF-8 stream.

Enumerator
byteOrderMark1
byteOrderMark2
byteOrderMark3

Constructor & Destructor Documentation

CharPointer_UTF8() [1/2]

CharPointer_UTF8::CharPointer_UTF8 ( const CharType * rawPointer )

explicitnoexcept

Referenced by atomicSwap(), findTerminatingNull(), operator+(), and operator-().

CharPointer_UTF8() [2/2]

CharPointer_UTF8::CharPointer_UTF8 ( const CharPointer_UTF8 & other )

default

Member Function Documentation

operator=() [1/2]

CharPointer_UTF8 & CharPointer_UTF8::operator= ( const CharPointer_UTF8 & other )

defaultnoexcept

operator=() [2/2]

CharPointer_UTF8 & CharPointer_UTF8::operator= ( const CharType * text )

noexcept

operator==()

bool CharPointer_UTF8::operator== ( CharPointer_UTF8 other ) const

noexcept

This is a pointer comparison, it doesn't compare the actual text.

operator!=()

bool CharPointer_UTF8::operator!= ( CharPointer_UTF8 other ) const

noexcept

operator<=()

bool CharPointer_UTF8::operator<= ( CharPointer_UTF8 other ) const

noexcept

operator<()

bool CharPointer_UTF8::operator< ( CharPointer_UTF8 other ) const

noexcept

operator>=()

bool CharPointer_UTF8::operator>= ( CharPointer_UTF8 other ) const

noexcept

operator>()

bool CharPointer_UTF8::operator> ( CharPointer_UTF8 other ) const

noexcept

getAddress()

CharType * CharPointer_UTF8::getAddress ( ) const

noexcept

Returns the address that this pointer is pointing to.

operator const CharType *()

CharPointer_UTF8::operator const CharType * ( ) const

noexcept

Returns the address that this pointer is pointing to.

isEmpty()

bool CharPointer_UTF8::isEmpty ( ) const

noexcept

Returns true if this pointer is pointing to a null character.

Referenced by CppTokeniserFunctions::StringIterator::isEOF().

isNotEmpty()

bool CharPointer_UTF8::isNotEmpty ( ) const

noexcept

Returns true if this pointer is not pointing to a null character.

operator*()

juce_wchar CharPointer_UTF8::operator* ( ) const

noexcept

Returns the unicode character that this pointer is pointing to.

operator++() [1/2]

CharPointer_UTF8 & CharPointer_UTF8::operator++ ( )

noexcept

Moves this pointer along to the next character in the string.

References jassert.

operator--()

CharPointer_UTF8 & CharPointer_UTF8::operator-- ( )

noexcept

Moves this pointer back to the previous character in the string.

getAndAdvance()

juce_wchar CharPointer_UTF8::getAndAdvance ( )

noexcept

Returns the character that this pointer is currently pointing to, and then advances the pointer to point to the next character.

Referenced by CppTokeniserFunctions::StringIterator::nextChar().

operator++() [2/2]

CharPointer_UTF8 CharPointer_UTF8::operator++ ( int )

noexcept

Moves this pointer along to the next character in the string.

operator+=()

CharPointer_UTF8 & CharPointer_UTF8::operator+= ( int numToSkip )

noexcept

Moves this pointer forwards by the specified number of characters.

Referenced by operator-=().

operator-=()

CharPointer_UTF8 & CharPointer_UTF8::operator-= ( int numToSkip )

noexcept

Moves this pointer backwards by the specified number of characters.

References operator+=().

operator[]()

juce_wchar CharPointer_UTF8::operator[] ( int characterIndex ) const

noexcept

Returns the character at a given character index from the start of the string.

operator+()

CharPointer_UTF8 CharPointer_UTF8::operator+ ( int numToSkip ) const

noexcept

Returns a pointer which is moved forwards from this one by the specified number of characters.

References CharPointer_UTF8().

operator-()

CharPointer_UTF8 CharPointer_UTF8::operator- ( int numToSkip ) const

noexcept

Returns a pointer which is moved backwards from this one by the specified number of characters.

References CharPointer_UTF8().

length()

size_t CharPointer_UTF8::length ( ) const

noexcept

Returns the number of characters in this string.

lengthUpTo() [1/2]

size_t CharPointer_UTF8::lengthUpTo ( const size_t maxCharsToCount ) const

noexcept

Returns the number of characters in this string, or the given value, whichever is lower.

References CharacterFunctions::lengthUpTo().

lengthUpTo() [2/2]

size_t CharPointer_UTF8::lengthUpTo ( const CharPointer_UTF8 end ) const

noexcept

Returns the number of characters in this string, or up to the given end pointer, whichever is lower.

References end(), and CharacterFunctions::lengthUpTo().

sizeInBytes()

size_t CharPointer_UTF8::sizeInBytes ( ) const

noexcept

Returns the number of bytes that are used to represent this string.

This includes the terminating null character.

References jassert, JUCE_BEGIN_IGNORE_WARNINGS_MSVC, and JUCE_END_IGNORE_WARNINGS_MSVC.

getBytesRequiredFor() [1/2]

static size_t CharPointer_UTF8::getBytesRequiredFor ( const juce_wchar charToWrite )

staticnoexcept

Returns the number of bytes that would be needed to represent the given unicode character in this encoding format.

Referenced by getBytesRequiredFor().

getBytesRequiredFor() [2/2]

template<class CharPointer >

static size_t CharPointer_UTF8::getBytesRequiredFor ( CharPointer text )

staticnoexcept

Returns the number of bytes that would be needed to represent the given string in this encoding format.

The value returned does NOT include the terminating null character.

References getBytesRequiredFor().

findTerminatingNull()

CharPointer_UTF8 CharPointer_UTF8::findTerminatingNull ( ) const

noexcept

Returns a pointer to the null character that terminates this string.

References CharPointer_UTF8().

write()

void CharPointer_UTF8::write ( const juce_wchar charToWrite )

noexcept

Writes a unicode character to this string, and advances this pointer to point to the next position.

Referenced by CppTokeniserFunctions::parseIdentifier().

writeNull()

void CharPointer_UTF8::writeNull ( ) const

noexcept

Writes a null character to this string (leaving the pointer's position unchanged).

Referenced by CppTokeniserFunctions::parseIdentifier().

writeAll() [1/2]

template<typename CharPointer >

void CharPointer_UTF8::writeAll ( const CharPointer src )

noexcept

Copies a source string to this pointer, advancing this pointer as it goes.

References CharacterFunctions::copyAll().

writeAll() [2/2]

void CharPointer_UTF8::writeAll ( const CharPointer_UTF8 src )

noexcept

Copies a source string to this pointer, advancing this pointer as it goes.

writeWithDestByteLimit()

template<typename CharPointer >

size_t CharPointer_UTF8::writeWithDestByteLimit ( const CharPointer src, const size_t maxDestBytes )

noexcept

Copies a source string to this pointer, advancing this pointer as it goes.

The maxDestBytes parameter specifies the maximum number of bytes that can be written to the destination buffer before stopping.

References CharacterFunctions::copyWithDestByteLimit().

writeWithCharLimit()

template<typename CharPointer >

void CharPointer_UTF8::writeWithCharLimit ( const CharPointer src, const int maxChars )

noexcept

Copies a source string to this pointer, advancing this pointer as it goes.

The maxChars parameter specifies the maximum number of characters that can be written to the destination buffer before stopping (including the terminating null).

References CharacterFunctions::copyWithCharLimit().

Referenced by String::appendCharPointer(), and String::appendCharPointer().

compare()

template<typename CharPointer >

int CharPointer_UTF8::compare ( const CharPointer other ) const

noexcept

Compares this string with another one.

References CharacterFunctions::compare().

compareUpTo()

template<typename CharPointer >

int CharPointer_UTF8::compareUpTo ( const CharPointer other, const int maxChars ) const

noexcept

Compares this string with another one, up to a specified number of characters.

References CharacterFunctions::compareUpTo().

compareIgnoreCase() [1/2]

template<typename CharPointer >

int CharPointer_UTF8::compareIgnoreCase ( const CharPointer other ) const

noexcept

Compares this string with another one.

References CharacterFunctions::compareIgnoreCase().

compareIgnoreCase() [2/2]

int CharPointer_UTF8::compareIgnoreCase ( const CharPointer_UTF8 other ) const

noexcept

Compares this string with another one.

References CharacterFunctions::compareIgnoreCase().

compareIgnoreCaseUpTo()

template<typename CharPointer >

int CharPointer_UTF8::compareIgnoreCaseUpTo ( const CharPointer other, const int maxChars ) const

noexcept

Compares this string with another one, up to a specified number of characters.

References CharacterFunctions::compareIgnoreCaseUpTo().

indexOf() [1/3]

template<typename CharPointer >

int CharPointer_UTF8::indexOf ( const CharPointer stringToFind ) const

noexcept

Returns the character index of a substring, or -1 if it isn't found.

References CharacterFunctions::indexOf().

indexOf() [2/3]

int CharPointer_UTF8::indexOf ( const juce_wchar charToFind ) const

noexcept

Returns the character index of a unicode character, or -1 if it isn't found.

References CharacterFunctions::indexOfChar().

indexOf() [3/3]

int CharPointer_UTF8::indexOf ( const juce_wchar charToFind, const bool ignoreCase ) const

noexcept

Returns the character index of a unicode character, or -1 if it isn't found.

References CharacterFunctions::indexOfChar(), and CharacterFunctions::indexOfCharIgnoreCase().

isWhitespace()

bool CharPointer_UTF8::isWhitespace ( ) const

noexcept

Returns true if the first character of this string is whitespace.

References CharacterFunctions::isWhitespace().

Referenced by CppTokeniserFunctions::StringIterator::skipWhitespace().

isDigit()

bool CharPointer_UTF8::isDigit ( ) const

noexcept

Returns true if the first character of this string is a digit.

isLetter()

bool CharPointer_UTF8::isLetter ( ) const

noexcept

Returns true if the first character of this string is a letter.

References CharacterFunctions::isLetter().

isLetterOrDigit()

bool CharPointer_UTF8::isLetterOrDigit ( ) const

noexcept

Returns true if the first character of this string is a letter or digit.

References CharacterFunctions::isLetterOrDigit().

isUpperCase()

bool CharPointer_UTF8::isUpperCase ( ) const

noexcept

Returns true if the first character of this string is upper-case.

References CharacterFunctions::isUpperCase().

isLowerCase()

bool CharPointer_UTF8::isLowerCase ( ) const

noexcept

Returns true if the first character of this string is lower-case.

References CharacterFunctions::isLowerCase().

toUpperCase()

juce_wchar CharPointer_UTF8::toUpperCase ( ) const

noexcept

Returns an upper-case version of the first character of this string.

References CharacterFunctions::toUpperCase().

toLowerCase()

juce_wchar CharPointer_UTF8::toLowerCase ( ) const

noexcept

Returns a lower-case version of the first character of this string.

References CharacterFunctions::toLowerCase().

getIntValue32()

int CharPointer_UTF8::getIntValue32 ( ) const

noexcept

Parses this string as a 32-bit integer.

getIntValue64()

int64 CharPointer_UTF8::getIntValue64 ( ) const

noexcept

Parses this string as a 64-bit integer.

getDoubleValue()

double CharPointer_UTF8::getDoubleValue ( ) const

noexcept

Parses this string as a floating point double.

References CharacterFunctions::getDoubleValue().

findEndOfWhitespace()

CharPointer_UTF8 CharPointer_UTF8::findEndOfWhitespace ( ) const

noexcept

Returns the first non-whitespace character in the string.

References CharacterFunctions::findEndOfWhitespace().

Referenced by Rectangle< ValueType >::fromString().

incrementToEndOfWhitespace()

void CharPointer_UTF8::incrementToEndOfWhitespace ( )

noexcept

Move this pointer to the first non-whitespace character in the string.

References CharacterFunctions::incrementToEndOfWhitespace().

canRepresent()

static bool CharPointer_UTF8::canRepresent ( juce_wchar character )

staticnoexcept

Returns true if the given unicode character can be represented in this encoding.

References CharacterFunctions::isNonSurrogateCodePoint().

isValidString()

static bool CharPointer_UTF8::isValidString ( const CharType * codeUnits, int maxBytesToRead )

static

Returns true if this data contains a valid string in this encoding.

References CharacterFunctions::isAscii().

atomicSwap()

CharPointer_UTF8 CharPointer_UTF8::atomicSwap

(

const CharPointer_UTF8

newValue

)

Atomically swaps this pointer for a new value, returning the previous value.

References CharPointer_UTF8().

isByteOrderMark()

static bool CharPointer_UTF8::isByteOrderMark ( const void * possibleByteOrder )

staticnoexcept

Returns true if the first three bytes in this pointer are the UTF8 byte-order mark (BOM).

The pointer must not be null, and must point to at least 3 valid bytes.

References byteOrderMark1, byteOrderMark2, byteOrderMark3, jassert, JUCE_BEGIN_IGNORE_WARNINGS_MSVC, and JUCE_END_IGNORE_WARNINGS_MSVC.

---

The documentation for this class was generated from the following file:

• juce_CharPointer_UTF8.h