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>

Collaboration diagram for CharPointer_UTF8:

[legend]

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

typedef char	CharType

Public Member Functions
	CharPointer_UTF8 (const CharType *rawPointer) noexcept

	CharPointer_UTF8 (const CharPointer_UTF8 &other) noexcept

CharPointer_UTF8	atomicSwap (const CharPointer_UTF8 newValue)
	Atomically swaps this pointer for a new value, returning the previous value. More...

template<typename CharPointer >
int	compare (const CharPointer other) const noexcept
	Compares this string with another one. More...

template<typename CharPointer >
int	compareIgnoreCase (const CharPointer other) const noexcept
	Compares this string with another one. More...

int	compareIgnoreCase (const CharPointer_UTF8 other) const noexcept
	Compares this string with another one. More...

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. More...

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. More...

CharPointer_UTF8	findEndOfWhitespace () const noexcept
	Returns the first non-whitespace character in the string. More...

CharPointer_UTF8	findTerminatingNull () const noexcept
	Returns a pointer to the null character that terminates this string. More...

CharType *	getAddress () const noexcept
	Returns the address that this pointer is pointing to. More...

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. More...

double	getDoubleValue () const noexcept
	Parses this string as a floating point double. More...

int	getIntValue32 () const noexcept
	Parses this string as a 32-bit integer. More...

int64	getIntValue64 () const noexcept
	Parses this string as a 64-bit integer. More...

template<typename CharPointer >
int	indexOf (const CharPointer stringToFind) const noexcept
	Returns the character index of a substring, or -1 if it isn't found. More...

int	indexOf (const juce_wchar charToFind) const noexcept
	Returns the character index of a unicode character, or -1 if it isn't found. More...

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. More...

bool	isDigit () const noexcept
	Returns true if the first character of this string is a digit. More...

bool	isEmpty () const noexcept
	Returns true if this pointer is pointing to a null character. More...

bool	isLetter () const noexcept
	Returns true if the first character of this string is a letter. More...

bool	isLetterOrDigit () const noexcept
	Returns true if the first character of this string is a letter or digit. More...

bool	isLowerCase () const noexcept
	Returns true if the first character of this string is lower-case. More...

bool	isNotEmpty () const noexcept
	Returns true if this pointer is not pointing to a null character. More...

bool	isUpperCase () const noexcept
	Returns true if the first character of this string is upper-case. More...

bool	isWhitespace () const noexcept
	Returns true if the first character of this string is whitespace. More...

size_t	length () const noexcept
	Returns the number of characters in this string. More...

size_t	lengthUpTo (const size_t maxCharsToCount) const noexcept
	Returns the number of characters in this string, or the given value, whichever is lower. More...

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. More...

	operator const CharType * () const noexcept
	Returns the address that this pointer is pointing to. More...

bool	operator!= (CharPointer_UTF8 other) const noexcept

juce_wchar	operator* () const noexcept
	Returns the unicode character that this pointer is pointing to. More...

CharPointer_UTF8	operator+ (int numToSkip) const noexcept
	Returns a pointer which is moved forwards from this one by the specified number of characters. More...

CharPointer_UTF8 &	operator++ () noexcept
	Moves this pointer along to the next character in the string. More...

CharPointer_UTF8	operator++ (int) noexcept
	Moves this pointer along to the next character in the string. More...

void	operator+= (int numToSkip) noexcept
	Moves this pointer forwards by the specified number of characters. More...

CharPointer_UTF8	operator- (int numToSkip) const noexcept
	Returns a pointer which is moved backwards from this one by the specified number of characters. More...

CharPointer_UTF8	operator-- () noexcept
	Moves this pointer back to the previous character in the string. More...

void	operator-= (int numToSkip) noexcept
	Moves this pointer backwards by the specified number of characters. More...

bool	operator< (CharPointer_UTF8 other) const noexcept

bool	operator<= (CharPointer_UTF8 other) const noexcept

CharPointer_UTF8	operator= (CharPointer_UTF8 other) noexcept

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. More...

bool	operator> (CharPointer_UTF8 other) const noexcept

bool	operator>= (CharPointer_UTF8 other) const noexcept

juce_wchar	operator[] (int characterIndex) const noexcept
	Returns the character at a given character index from the start of the string. More...

size_t	sizeInBytes () const noexcept
	Returns the number of bytes that are used to represent this string. More...

juce_wchar	toLowerCase () const noexcept
	Returns a lower-case version of the first character of this string. More...

juce_wchar	toUpperCase () const noexcept
	Returns an upper-case version of the first character of this string. More...

void	write (const juce_wchar charToWrite) noexcept
	Writes a unicode character to this string, and advances this pointer to point to the next position. More...

template<typename CharPointer >
void	writeAll (const CharPointer src) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes. More...

void	writeAll (const CharPointer_UTF8 src) noexcept
	Copies a source string to this pointer, advancing this pointer as it goes. More...

void	writeNull () const noexcept
	Writes a null character to this string (leaving the pointer's position unchanged). More...

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. More...

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. More...

Static Public Member Functions
static bool	canRepresent (juce_wchar character) noexcept
	Returns true if the given unicode character can be represented in this encoding. More...

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. More...

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. More...

static bool	isByteOrderMark (const void *possibleByteOrder) noexcept
	Returns true if the first three bytes in this pointer are the UTF8 byte-order mark (BOM). More...

static bool	isValidString (const CharType *dataToTest, int maxBytesToRead)
	Returns true if this data contains a valid string in this encoding. More...

Private Attributes
CharType *	data

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

typedef char CharPointer_UTF8::CharType

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 )

inlineexplicitnoexcept

Referenced by atomicSwap(), and findTerminatingNull().

◆ CharPointer_UTF8() [2/2]

CharPointer_UTF8::CharPointer_UTF8 ( const CharPointer_UTF8 & other )

inlinenoexcept

Member Function Documentation

◆ atomicSwap()

CharPointer_UTF8 CharPointer_UTF8::atomicSwap ( const CharPointer_UTF8 newValue )

inline

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

References CharPointer_UTF8(), and data.

◆ canRepresent()

static bool CharPointer_UTF8::canRepresent ( juce_wchar character )

inlinestaticnoexcept

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

◆ compare()

template<typename CharPointer >

int CharPointer_UTF8::compare ( const CharPointer other ) const

inlinenoexcept

Compares this string with another one.

References CharacterFunctions::compare().

◆ compareIgnoreCase() [1/2]

template<typename CharPointer >

int CharPointer_UTF8::compareIgnoreCase ( const CharPointer other ) const

inlinenoexcept

Compares this string with another one.

References CharacterFunctions::compareIgnoreCase().

◆ compareIgnoreCase() [2/2]

int CharPointer_UTF8::compareIgnoreCase ( const CharPointer_UTF8 other ) const

inlinenoexcept

Compares this string with another one.

References CharacterFunctions::compareIgnoreCase().

◆ compareIgnoreCaseUpTo()

template<typename CharPointer >

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

inlinenoexcept

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

References CharacterFunctions::compareIgnoreCaseUpTo().

◆ compareUpTo()

template<typename CharPointer >

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

inlinenoexcept

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

References CharacterFunctions::compareUpTo().

◆ findEndOfWhitespace()

CharPointer_UTF8 CharPointer_UTF8::findEndOfWhitespace ( ) const

inlinenoexcept

Returns the first non-whitespace character in the string.

References CharacterFunctions::findEndOfWhitespace().

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

◆ findTerminatingNull()

CharPointer_UTF8 CharPointer_UTF8::findTerminatingNull ( ) const

inlinenoexcept

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

References CharPointer_UTF8(), and data.

◆ getAddress()

CharType* CharPointer_UTF8::getAddress ( ) const

inlinenoexcept

Returns the address that this pointer is pointing to.

References data.

Referenced by DynamicLibrary::open().

◆ getAndAdvance()

juce_wchar CharPointer_UTF8::getAndAdvance ( )

inlinenoexcept

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

References data.

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

◆ getBytesRequiredFor() [1/2]

static size_t CharPointer_UTF8::getBytesRequiredFor ( const juce_wchar charToWrite )

inlinestaticnoexcept

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 )

inlinestaticnoexcept

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().

◆ getDoubleValue()

double CharPointer_UTF8::getDoubleValue ( ) const

inlinenoexcept

Parses this string as a floating point double.

References CharacterFunctions::getDoubleValue().

◆ getIntValue32()

int CharPointer_UTF8::getIntValue32 ( ) const

inlinenoexcept

Parses this string as a 32-bit integer.

References data.

◆ getIntValue64()

int64 CharPointer_UTF8::getIntValue64 ( ) const

inlinenoexcept

Parses this string as a 64-bit integer.

References data.

◆ indexOf() [1/3]

template<typename CharPointer >

int CharPointer_UTF8::indexOf ( const CharPointer stringToFind ) const

inlinenoexcept

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

inlinenoexcept

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

inlinenoexcept

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

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

◆ isByteOrderMark()

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

inlinestaticnoexcept

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, and jassert.

◆ isDigit()

bool CharPointer_UTF8::isDigit ( ) const

inlinenoexcept

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

References data.

◆ isEmpty()

bool CharPointer_UTF8::isEmpty ( ) const

inlinenoexcept

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

References data.

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

◆ isLetter()

bool CharPointer_UTF8::isLetter ( ) const

inlinenoexcept

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

References CharacterFunctions::isLetter().

◆ isLetterOrDigit()

bool CharPointer_UTF8::isLetterOrDigit ( ) const

inlinenoexcept

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

References CharacterFunctions::isLetterOrDigit().

◆ isLowerCase()

bool CharPointer_UTF8::isLowerCase ( ) const

inlinenoexcept

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

References CharacterFunctions::isLowerCase().

◆ isNotEmpty()

bool CharPointer_UTF8::isNotEmpty ( ) const

inlinenoexcept

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

References data.

◆ isUpperCase()

bool CharPointer_UTF8::isUpperCase ( ) const

inlinenoexcept

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

References CharacterFunctions::isUpperCase().

◆ isValidString()

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

inlinestatic

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

◆ isWhitespace()

bool CharPointer_UTF8::isWhitespace ( ) const

inlinenoexcept

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

References data.

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

◆ length()

size_t CharPointer_UTF8::length ( ) const

inlinenoexcept

Returns the number of characters in this string.

References data.

◆ lengthUpTo() [1/2]

size_t CharPointer_UTF8::lengthUpTo ( const size_t maxCharsToCount ) const

inlinenoexcept

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

inlinenoexcept

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

References CharacterFunctions::lengthUpTo().

◆ operator const CharType *()

CharPointer_UTF8::operator const CharType * ( ) const

inlinenoexcept

Returns the address that this pointer is pointing to.

References data.

◆ operator!=()

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

inlinenoexcept

References data.

◆ operator*()

juce_wchar CharPointer_UTF8::operator* ( ) const

inlinenoexcept

Returns the unicode character that this pointer is pointing to.

References data.

◆ operator+()

CharPointer_UTF8 CharPointer_UTF8::operator+ ( int numToSkip ) const

inlinenoexcept

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

◆ operator++() [1/2]

CharPointer_UTF8& CharPointer_UTF8::operator++ ( )

inlinenoexcept

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

References data, and jassert.

◆ operator++() [2/2]

CharPointer_UTF8 CharPointer_UTF8::operator++ ( int )

inlinenoexcept

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

◆ operator+=()

void CharPointer_UTF8::operator+= ( int numToSkip )

inlinenoexcept

Moves this pointer forwards by the specified number of characters.

Referenced by operator-=().

◆ operator-()

CharPointer_UTF8 CharPointer_UTF8::operator- ( int numToSkip ) const

inlinenoexcept

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

◆ operator--()

CharPointer_UTF8 CharPointer_UTF8::operator-- ( )

inlinenoexcept

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

References data.

◆ operator-=()

void CharPointer_UTF8::operator-= ( int numToSkip )

inlinenoexcept

Moves this pointer backwards by the specified number of characters.

References operator+=().

◆ operator<()

bool CharPointer_UTF8::operator< ( CharPointer_UTF8 other ) const

inlinenoexcept

References data.

◆ operator<=()

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

inlinenoexcept

References data.

◆ operator=() [1/2]

CharPointer_UTF8 CharPointer_UTF8::operator= ( CharPointer_UTF8 other )

inlinenoexcept

References data.

◆ operator=() [2/2]

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

inlinenoexcept

References data.

◆ operator==()

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

inlinenoexcept

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

References data.

◆ operator>()

bool CharPointer_UTF8::operator> ( CharPointer_UTF8 other ) const

inlinenoexcept

References data.

◆ operator>=()

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

inlinenoexcept

References data.

◆ operator[]()

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

inlinenoexcept

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

◆ sizeInBytes()

size_t CharPointer_UTF8::sizeInBytes ( ) const

inlinenoexcept

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

This includes the terminating null character.

References data, and jassert.

◆ toLowerCase()

juce_wchar CharPointer_UTF8::toLowerCase ( ) const

inlinenoexcept

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

References CharacterFunctions::toLowerCase().

◆ toUpperCase()

juce_wchar CharPointer_UTF8::toUpperCase ( ) const

inlinenoexcept

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

References CharacterFunctions::toUpperCase().

◆ write()

void CharPointer_UTF8::write ( const juce_wchar charToWrite )

inlinenoexcept

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

References data.

Referenced by anonymous_namespace{juce_android_JNIHelpers.h}::javaStringFromChar(), and CppTokeniserFunctions::parseIdentifier().

◆ writeAll() [1/2]

template<typename CharPointer >

void CharPointer_UTF8::writeAll ( const CharPointer src )

inlinenoexcept

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 )

inlinenoexcept

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

References data.

◆ writeNull()

void CharPointer_UTF8::writeNull ( ) const

inlinenoexcept

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

References data.

Referenced by CppTokeniserFunctions::parseIdentifier().

◆ writeWithCharLimit()

template<typename CharPointer >

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

inlinenoexcept

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().

◆ writeWithDestByteLimit()

template<typename CharPointer >

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

inlinenoexcept

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().

Member Data Documentation

◆ data

CharType* CharPointer_UTF8::data

private

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

juce_CharPointer_UTF8.h

Public Types

Public Member Functions

Static Public Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

◆ CharType

Member Enumeration Documentation

◆ anonymous enum

Constructor & Destructor Documentation

◆ CharPointer_UTF8() [1/2]

◆ CharPointer_UTF8() [2/2]

Member Function Documentation

◆ atomicSwap()

◆ canRepresent()

◆ compare()

◆ compareIgnoreCase() [1/2]

◆ compareIgnoreCase() [2/2]

◆ compareIgnoreCaseUpTo()

◆ compareUpTo()

◆ findEndOfWhitespace()

◆ findTerminatingNull()

◆ getAddress()

◆ getAndAdvance()

◆ getBytesRequiredFor() [1/2]

◆ getBytesRequiredFor() [2/2]

◆ getDoubleValue()

◆ getIntValue32()

◆ getIntValue64()

◆ indexOf() [1/3]

◆ indexOf() [2/3]

◆ indexOf() [3/3]

◆ isByteOrderMark()

◆ isDigit()

◆ isEmpty()

◆ isLetter()

◆ isLetterOrDigit()

◆ isLowerCase()

◆ isNotEmpty()

◆ isUpperCase()

◆ isValidString()

◆ isWhitespace()

◆ length()

◆ lengthUpTo() [1/2]

◆ lengthUpTo() [2/2]

◆ operator const CharType *()

◆ operator!=()

◆ operator*()

◆ operator+()

◆ operator++() [1/2]

◆ operator++() [2/2]

◆ operator+=()

◆ operator-()

◆ operator--()

◆ operator-=()

◆ operator<()

◆ operator<=()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ operator==()

◆ operator>()

◆ operator>=()

◆ operator[]()

◆ sizeInBytes()

◆ toLowerCase()

◆ toUpperCase()

◆ write()

◆ writeAll() [1/2]

◆ writeAll() [2/2]

◆ writeNull()

◆ writeWithCharLimit()

◆ writeWithDestByteLimit()

Member Data Documentation

◆ data