CStringUTF8 Class Reference
[String Manipulations]

#include <ncbistr.hpp>

Detailed Description

Definition at line 2076 of file ncbistr.hpp.

Public Types

enum EValidate { eNoValidate, eValidate }

Public Member Functions

CStringUTF8 (void)

Default constructor.

~CStringUTF8 (void)

Destructor.

CStringUTF8 (const CStringUTF8 &src, EValidate validate=eNoValidate)

Copy constructor.

CStringUTF8 (const string &src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)

Constructor from a C++ string.

CStringUTF8 (const char *src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)

Constructor from a C string.

template<class T>

CStringUTF8 (const basic_string< T > &src)

Constructor from any string (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).

template<typename TChar>

CStringUTF8 (const TChar *src)

Constructor from any character sequence (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).

CStringUTF8 & operator= (const CStringUTF8 &src)

Assign to UTF8 string.

template<typename TChar>

CStringUTF8 & operator= (const basic_string< TChar > &src)

Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

template<typename TChar>

CStringUTF8 & operator= (const TChar *src)

Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

CStringUTF8 & operator+= (const CStringUTF8 &src)

Append a string in UTF8 encoding.

template<typename TChar>

CStringUTF8 & operator+= (const basic_string< TChar > &src)

Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

template<typename TChar>

CStringUTF8 & operator+= (const TChar *src)

Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

CStringUTF8 & Assign (const string &src, EEncoding encoding, EValidate validate=eNoValidate)

Assign to C++ string.

CStringUTF8 & Assign (const char *src, EEncoding encoding, EValidate validate=eNoValidate)

Assign to C string.

template<typename TChar>

CStringUTF8 & Assign (const basic_string< TChar > &src)

Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

template<typename TChar>

CStringUTF8 & Assign (const TChar *src)

Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

CStringUTF8 & Assign (char ch, EEncoding encoding)

Assign to a single character.

CStringUTF8 & Append (const string &src, EEncoding encoding, EValidate validate=eNoValidate)

Append a C++ string.

CStringUTF8 & Append (const char *src, EEncoding encoding, EValidate validate=eNoValidate)

Append a C string.

template<typename TChar>

CStringUTF8 & Append (const basic_string< TChar > &src)

Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

template<typename TChar>

CStringUTF8 & Append (const TChar *src)

Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

CStringUTF8 & Append (char ch, EEncoding encoding)

Append single character.

CStringUTF8 & Append (TUnicodeSymbol ch)

Append single Unicode code point.

SIZE_TYPE GetSymbolCount (void) const

Get the number of symbols (code points) in the string.

bool IsValid (void) const

Check that the character encoding of the string is valid UTF-8.

string AsLatin1 (const char *substitute_on_error=0) const

Convert to ISO 8859-1 (Latin1) character representation.

string AsSingleByteString (EEncoding encoding, const char *substitute_on_error=0) const

Convert the string to a single-byte character representation.

TStringUCS2 AsUCS2 (const TCharUCS2 *substitute_on_error=0) const

Convert to UCS-2 for all platforms.

Static Public Member Functions

static SIZE_TYPE GetValidSymbolCount (const char *src, SIZE_TYPE buf_size)

Get the number of valid UTF-8 symbols (code points) in the buffer.

static SIZE_TYPE GetValidBytesCount (const char *src, SIZE_TYPE buf_size)

Get the number of valid UTF-8 bytes (code units) in the buffer.

static EEncoding GuessEncoding (const char *src)

Guess the encoding of the C string.

static EEncoding GuessEncoding (const string &src)

Guess the encoding of the C++ string.

static bool MatchEncoding (const char *src, EEncoding encoding)

Check the encoding of the C string.

static bool MatchEncoding (const string &src, EEncoding encoding)

Check the encoding of the C++ string.

static TUnicodeSymbol CharToSymbol (char ch, EEncoding encoding)

Convert encoded character into UTF16.

static char SymbolToChar (TUnicodeSymbol sym, EEncoding encoding)

Convert Unicode code point into encoded character.

static TUnicodeSymbol Decode (const char *&src)

Convert sequence of UTF8 code units into Unicode code point.

static TUnicodeSymbol DecodeFirst (char ch, SIZE_TYPE &more)

Convert first character of UTF8 sequence into Unicode.

static TUnicodeSymbol DecodeNext (TUnicodeSymbol chU, char ch)

Convert next character of UTF8 sequence into Unicode.

Private Member Functions

string AsAscii (void) const

Function AsAscii is deprecated - use AsLatin1() instead.

template<typename TChar>

basic_string< TChar > x_AsBasicString (const TChar *substitute_on_error) const

Conversion to basic_string with any base type we need.

void x_Validate (void) const

void x_AppendChar (TUnicodeSymbol ch)

Convert Unicode code point into UTF8 and append.

void x_Append (const char *src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)

Convert coded character sequence into UTF8 and append.

template<typename TChar>

void x_Append (const TChar *src)

Convert Unicode character sequence into UTF8 and append Sequence can be in UCS-4 (TChar == (U)Int4), UCS-2 (TChar == (U)Int2) or in ISO8859-1 (TChar == char).

Static Private Member Functions

static SIZE_TYPE x_BytesNeeded (TUnicodeSymbol ch)

Check how many bytes is needed to represent the code point in UTF8.

static bool x_EvalFirst (char ch, SIZE_TYPE &more)

Check if the character is valid first code unit of UTF8.

static bool x_EvalNext (char ch)

Check if the character is valid non-first code unit of UTF8.

Member Enumeration Documentation

enum CStringUTF8::EValidate

Enumerator:

eNoValidate

eValidate

Definition at line 2079 of file ncbistr.hpp.

Constructor & Destructor Documentation

CStringUTF8::CStringUTF8 ( void ) [inline]

Default constructor.

Definition at line 2085 of file ncbistr.hpp.

CStringUTF8::~CStringUTF8 ( void ) [inline]

Destructor.

Definition at line 2090 of file ncbistr.hpp.

CStringUTF8::CStringUTF8 ( const CStringUTF8 & src,

EValidate validate = eNoValidate

) [inline]

Copy constructor.

Parameters:

src Source UTF-8 string

validate Verify that the source character encoding is really UTF-8

Definition at line 2100 of file ncbistr.hpp.

CStringUTF8::CStringUTF8 ( const string & src,

EEncoding encoding = eEncoding_ISO8859_1,

EValidate validate = eNoValidate

) [inline]

Constructor from a C++ string.

Parameters:

src Source string

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2116 of file ncbistr.hpp.

CStringUTF8::CStringUTF8 ( const char * src,

EEncoding encoding = eEncoding_ISO8859_1,

EValidate validate = eNoValidate

) [inline]

Constructor from a C string.

Parameters:

src Source zero-terminated character buffer

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2132 of file ncbistr.hpp.

template<class T>

CStringUTF8::CStringUTF8 ( const basic_string< T > & src ) [inline]

Constructor from any string (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).

Definition at line 2143 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8::CStringUTF8 ( const TChar * src ) [inline]

Constructor from any character sequence (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).

Definition at line 2152 of file ncbistr.hpp.

Member Function Documentation

CStringUTF8& CStringUTF8::Append ( TUnicodeSymbol ch ) [inline]

Append single Unicode code point.

Parameters:

ch Unicode code point

Definition at line 2357 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::Append ( char ch,

EEncoding encoding

) [inline]

Append single character.

Parameters:

ch Character

encoding Character encoding

Definition at line 2346 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::Append ( const TChar * src ) [inline]

Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Parameters:

src Source zero-terminated character buffer

Definition at line 2334 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::Append ( const basic_string< TChar > & src ) [inline]

Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Parameters:

src Source string

Definition at line 2322 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::Append ( const char * src,

EEncoding encoding,

EValidate validate = eNoValidate

) [inline]

Append a C string.

Parameters:

src Source zero-terminated character buffer

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2308 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::Append ( const string & src,

EEncoding encoding,

EValidate validate = eNoValidate

) [inline]

Append a C++ string.

Parameters:

src Source string

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2292 of file ncbistr.hpp.

string CStringUTF8::AsAscii ( void ) const [inline, private]

Function AsAscii is deprecated - use AsLatin1() instead.

Definition at line 2551 of file ncbistr.hpp.

string CStringUTF8::AsLatin1 ( const char * substitute_on_error = 0 ) const [inline]

Convert to ISO 8859-1 (Latin1) character representation.
Can throw a CStringException if the conversion is impossible or the string has invalid UTF-8 format.
Parameters:

substitute_on_error If the conversion is impossible, append the provided string or, if substitute_on_error equals 0, throw the exception

Definition at line 2404 of file ncbistr.hpp.
References eEncoding_ISO8859_1.

CStringUTF8& CStringUTF8::Assign ( char ch,

EEncoding encoding

) [inline]

Assign to a single character.

Parameters:

ch Character

encoding Character encoding

Definition at line 2276 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::Assign ( const TChar * src ) [inline]

Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Parameters:

src Source zero-terminated character buffer

Definition at line 2263 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::Assign ( const basic_string< TChar > & src ) [inline]

Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Parameters:

src Source string

Definition at line 2250 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::Assign ( const char * src,

EEncoding encoding,

EValidate validate = eNoValidate

) [inline]

Assign to C string.

Parameters:

src Source zero-terminated character buffer

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2235 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::Assign ( const string & src,

EEncoding encoding,

EValidate validate = eNoValidate

) [inline]

Assign to C++ string.

Parameters:

src Source string

encoding Character encoding of the source string

validate Verify the character encoding of the source

Definition at line 2218 of file ncbistr.hpp.
Referenced by CObjectOStreamXml::WriteEncodedChar(), CObjectOStreamJson::WriteEncodedChar(), and CWString::x_StringToUTF8().

string CStringUTF8::AsSingleByteString ( EEncoding encoding,

const char * substitute_on_error = 0

) const

Convert the string to a single-byte character representation.
Can throw a CStringException if the conversion is impossible or the string has invalid UTF-8 format.
Parameters:

encoding Desired encoding

substitute_on_error If the conversion is impossible, append the provided string or, if substitute_on_error equals 0, throw the exception

Returns:
C++ string

Definition at line 3260 of file ncbistr.cpp.
References Decode(), GetSymbolCount(), and SymbolToChar().
Referenced by CWString::x_UTF8ToString().

TStringUCS2 CStringUTF8::AsUCS2 ( const TCharUCS2 * substitute_on_error = 0 ) const [inline]

Convert to UCS-2 for all platforms.
Can throw a CStringException if the conversion is impossible or the string has invalid UTF-8 format.

Parameters:

substitute_on_error If the conversion is impossible, append the provided string or, if substitute_on_error equals 0, throw the exception

Definition at line 2448 of file ncbistr.hpp.

TUnicodeSymbol CStringUTF8::CharToSymbol ( char ch,

EEncoding encoding

) [static]

Convert encoded character into UTF16.

Parameters:

ch Encoded character

encoding Character encoding

Returns:
Code point

Definition at line 3362 of file ncbistr.cpp.
References eEncoding_Ascii, eEncoding_ISO8859_1, eEncoding_Unknown, eEncoding_UTF8, eEncoding_Windows_1252, and NCBI_THROW2.
Referenced by CObjectOStreamXml::WriteEncodedChar(), and x_Append().

TUnicodeSymbol CStringUTF8::Decode ( const char *& src ) [static]

Convert sequence of UTF8 code units into Unicode code point.

Parameters:

src UTF8 zero-terminated buffer

Returns:
Unicode code point

Definition at line 3523 of file ncbistr.cpp.
References NCBI_THROW2.
Referenced by AsSingleByteString(), CObjectOStreamXml::WriteEncodedChar(), and x_AsBasicString().

TUnicodeSymbol CStringUTF8::DecodeFirst ( char ch,

SIZE_TYPE & more

) [static]

Convert first character of UTF8 sequence into Unicode.

Parameters:

ch character

more if the character is valid, - how many more characters to expect

Returns:
non-zero, if the character is valid

Definition at line 3556 of file ncbistr.cpp.
Referenced by CObjectIStreamXml::ReadUtf8Char().

TUnicodeSymbol CStringUTF8::DecodeNext ( TUnicodeSymbol chU,

char ch

) [static]

Convert next character of UTF8 sequence into Unicode.

Parameters:

ch character

ch16 Unicode character

Returns:
non-zero, if the character is valid

Definition at line 3576 of file ncbistr.cpp.
Referenced by CObjectIStreamXml::ReadUtf8Char().

SIZE_TYPE CStringUTF8::GetSymbolCount ( void ) const

Get the number of symbols (code points) in the string.

Returns:
Number of symbols (code points)

Definition at line 3202 of file ncbistr.cpp.
References NCBI_THROW2, s_DiffPtr(), x_EvalFirst(), and x_EvalNext().
Referenced by AsSingleByteString(), CWString::GetSymbolNum(), and x_AsBasicString().

SIZE_TYPE CStringUTF8::GetValidBytesCount ( const char * src,

SIZE_TYPE buf_size

) [static]

Get the number of valid UTF-8 bytes (code units) in the buffer.

Parameters:

src Character buffer

buf_size The number of bytes in the buffer

Returns:
Number of valid bytes (no exception thrown)

Definition at line 3238 of file ncbistr.cpp.
References x_EvalFirst(), and x_EvalNext().
Referenced by CODBC_BCPInCmd::Send(), CODBC_SendDataCmd::SendChunk(), CTL_SendDataCmd::SendChunk(), and CODBC_Connection::x_SendData().

SIZE_TYPE CStringUTF8::GetValidSymbolCount ( const char * src,

SIZE_TYPE buf_size

) [static]

Get the number of valid UTF-8 symbols (code points) in the buffer.

Parameters:

src Character buffer

buf_size The number of bytes in the buffer

Returns:
Number of valid symbols (no exception thrown)

Definition at line 3221 of file ncbistr.cpp.
References x_EvalFirst(), and x_EvalNext().

static EEncoding CStringUTF8::GuessEncoding ( const string & src ) [inline, static]

Guess the encoding of the C++ string.
It can distinguish between UTF-8, Latin1, and Win1252 only
Parameters:

src Source string

Returns:
Encoding

Definition at line 2469 of file ncbistr.hpp.

EEncoding CStringUTF8::GuessEncoding ( const char * src ) [static]

Guess the encoding of the C string.
It can distinguish between UTF-8, Latin1, and Win1252 only
Parameters:

src Source zero-terminated character buffer

Returns:
Encoding

Definition at line 3282 of file ncbistr.cpp.
References skip, utf8, and x_EvalNext().
Referenced by CHTMLHelper::HTMLDecode(), MatchEncoding(), and x_Append().

bool CStringUTF8::IsValid ( void ) const [inline]

Check that the character encoding of the string is valid UTF-8.

Returns:
Result of the check

Definition at line 2393 of file ncbistr.hpp.
References eEncoding_UTF8.
Referenced by x_Validate().

static bool CStringUTF8::MatchEncoding ( const string & src,

EEncoding encoding

) [inline, static]

Check the encoding of the C++ string.
Check that the encoding of the source is the same, or is compatible with the specified one
Parameters:

src Source string

encoding Character encoding form to check against

Returns:
Boolean result: encoding is same or compatible

Definition at line 2496 of file ncbistr.hpp.

bool CStringUTF8::MatchEncoding ( const char * src,

EEncoding encoding

) [static]

Check the encoding of the C string.
Check that the encoding of the source is the same, or is compatible with the specified one
Parameters:

src Source string

encoding Character encoding form to check against

Returns:
Boolean result: encoding is same or compatible

Definition at line 3329 of file ncbistr.cpp.
References eEncoding_Ascii, eEncoding_ISO8859_1, eEncoding_Unknown, eEncoding_UTF8, eEncoding_Windows_1252, and GuessEncoding().
Referenced by x_Append().

template<typename TChar>

CStringUTF8& CStringUTF8::operator+= ( const TChar * src ) [inline]

Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Definition at line 2204 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::operator+= ( const basic_string< TChar > & src ) [inline]

Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Definition at line 2195 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::operator+= ( const CStringUTF8 & src ) [inline]

Append a string in UTF8 encoding.

Definition at line 2186 of file ncbistr.hpp.
References operator+=().

template<typename TChar>

CStringUTF8& CStringUTF8::operator= ( const TChar * src ) [inline]

Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Definition at line 2178 of file ncbistr.hpp.

template<typename TChar>

CStringUTF8& CStringUTF8::operator= ( const basic_string< TChar > & src ) [inline]

Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).

Definition at line 2168 of file ncbistr.hpp.

CStringUTF8& CStringUTF8::operator= ( const CStringUTF8 & src ) [inline]

Assign to UTF8 string.

Definition at line 2159 of file ncbistr.hpp.

char CStringUTF8::SymbolToChar ( TUnicodeSymbol sym,

EEncoding encoding

) [static]

Convert Unicode code point into encoded character.

Parameters:

ch Code point

encoding Character encoding

Returns:
Encoded character

Definition at line 3387 of file ncbistr.cpp.
References eEncoding_Unknown, eEncoding_UTF8, eEncoding_Windows_1252, and NCBI_THROW2.
Referenced by AsSingleByteString(), and CObjectOStreamXml::WriteEncodedChar().

template<typename TChar>

void CStringUTF8::x_Append ( const TChar * src ) [inline, private]

Convert Unicode character sequence into UTF8 and append Sequence can be in UCS-4 (TChar == (U)Int4), UCS-2 (TChar == (U)Int2) or in ISO8859-1 (TChar == char).

Definition at line 3648 of file ncbistr.hpp.
References x_BytesNeeded().

void CStringUTF8::x_Append ( const char * src,

EEncoding encoding = eEncoding_ISO8859_1,

EValidate validate = eNoValidate

) [private]

Convert coded character sequence into UTF8 and append.

Definition at line 3442 of file ncbistr.cpp.
References CharToSymbol(), eEncoding_Ascii, eEncoding_Unknown, eEncoding_UTF8, eValidate, GuessEncoding(), MatchEncoding(), NCBI_THROW2, and x_BytesNeeded().

void CStringUTF8::x_AppendChar ( TUnicodeSymbol ch ) [private]

Convert Unicode code point into UTF8 and append.

Definition at line 3420 of file ncbistr.cpp.

template<typename TChar>

basic_string< TChar > CStringUTF8::x_AsBasicString ( const TChar * substitute_on_error ) const [inline, private]

Conversion to basic_string with any base type we need.

Definition at line 3622 of file ncbistr.hpp.
References Decode(), and GetSymbolCount().

SIZE_TYPE CStringUTF8::x_BytesNeeded ( TUnicodeSymbol ch ) [static, private]

Check how many bytes is needed to represent the code point in UTF8.

Definition at line 3477 of file ncbistr.cpp.
Referenced by x_Append().

bool CStringUTF8::x_EvalFirst ( char ch,

SIZE_TYPE & more

) [static, private]

Check if the character is valid first code unit of UTF8.

Definition at line 3491 of file ncbistr.cpp.
Referenced by GetSymbolCount(), GetValidBytesCount(), and GetValidSymbolCount().

bool CStringUTF8::x_EvalNext ( char ch ) [static, private]

Check if the character is valid non-first code unit of UTF8.

Definition at line 3517 of file ncbistr.cpp.
Referenced by GetSymbolCount(), GetValidBytesCount(), GetValidSymbolCount(), and GuessEncoding().

void CStringUTF8::x_Validate ( void ) const [private]

Definition at line 3411 of file ncbistr.cpp.
References IsValid(), and NCBI_THROW2.

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

include/corelib/ncbistr.hpp
src/corelib/ncbistr.cpp

Generated on Mon Dec 7 14:48:07 2009 for NCBI C++ ToolKit by

1.4.6

Modified on Mon Dec 07 16:24:11 2009 by modify_doxy.py rev. 173732


Public Types
enum	EValidate { eNoValidate, eValidate }
Public Member Functions
	CStringUTF8 (void)
	Default constructor.
	~CStringUTF8 (void)
	Destructor.
	CStringUTF8 (const CStringUTF8 &src, EValidate validate=eNoValidate)
	Copy constructor.
	CStringUTF8 (const string &src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)
	Constructor from a C++ string.
	CStringUTF8 (const char *src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)
	Constructor from a C string.
template<class T>
	CStringUTF8 (const basic_string< T > &src)
	Constructor from any string (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).
template<typename TChar>
	CStringUTF8 (const TChar *src)
	Constructor from any character sequence (ISO8859-1, USC-2 or USC-4, depending on the size of TChar).
CStringUTF8 &	operator= (const CStringUTF8 &src)
	Assign to UTF8 string.
template<typename TChar>
CStringUTF8 &	operator= (const basic_string< TChar > &src)
	Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
template<typename TChar>
CStringUTF8 &	operator= (const TChar *src)
	Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
CStringUTF8 &	operator+= (const CStringUTF8 &src)
	Append a string in UTF8 encoding.
template<typename TChar>
CStringUTF8 &	operator+= (const basic_string< TChar > &src)
	Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
template<typename TChar>
CStringUTF8 &	operator+= (const TChar *src)
	Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
CStringUTF8 &	Assign (const string &src, EEncoding encoding, EValidate validate=eNoValidate)
	Assign to C++ string.
CStringUTF8 &	Assign (const char *src, EEncoding encoding, EValidate validate=eNoValidate)
	Assign to C string.
template<typename TChar>
CStringUTF8 &	Assign (const basic_string< TChar > &src)
	Assign to C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
template<typename TChar>
CStringUTF8 &	Assign (const TChar *src)
	Assign to C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
CStringUTF8 &	Assign (char ch, EEncoding encoding)
	Assign to a single character.
CStringUTF8 &	Append (const string &src, EEncoding encoding, EValidate validate=eNoValidate)
	Append a C++ string.
CStringUTF8 &	Append (const char *src, EEncoding encoding, EValidate validate=eNoValidate)
	Append a C string.
template<typename TChar>
CStringUTF8 &	Append (const basic_string< TChar > &src)
	Append a C++ string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
template<typename TChar>
CStringUTF8 &	Append (const TChar *src)
	Append a C string in ISO8859-1, USC-2 or USC-4 (depending on the size of TChar).
CStringUTF8 &	Append (char ch, EEncoding encoding)
	Append single character.
CStringUTF8 &	Append (TUnicodeSymbol ch)
	Append single Unicode code point.
SIZE_TYPE	GetSymbolCount (void) const
	Get the number of symbols (code points) in the string.
bool	IsValid (void) const
	Check that the character encoding of the string is valid UTF-8.
string	AsLatin1 (const char *substitute_on_error=0) const
	Convert to ISO 8859-1 (Latin1) character representation.
string	AsSingleByteString (EEncoding encoding, const char *substitute_on_error=0) const
	Convert the string to a single-byte character representation.
TStringUCS2	AsUCS2 (const TCharUCS2 *substitute_on_error=0) const
	Convert to UCS-2 for all platforms.
Static Public Member Functions
static SIZE_TYPE	GetValidSymbolCount (const char *src, SIZE_TYPE buf_size)
	Get the number of valid UTF-8 symbols (code points) in the buffer.
static SIZE_TYPE	GetValidBytesCount (const char *src, SIZE_TYPE buf_size)
	Get the number of valid UTF-8 bytes (code units) in the buffer.
static EEncoding	GuessEncoding (const char *src)
	Guess the encoding of the C string.
static EEncoding	GuessEncoding (const string &src)
	Guess the encoding of the C++ string.
static bool	MatchEncoding (const char *src, EEncoding encoding)
	Check the encoding of the C string.
static bool	MatchEncoding (const string &src, EEncoding encoding)
	Check the encoding of the C++ string.
static TUnicodeSymbol	CharToSymbol (char ch, EEncoding encoding)
	Convert encoded character into UTF16.
static char	SymbolToChar (TUnicodeSymbol sym, EEncoding encoding)
	Convert Unicode code point into encoded character.
static TUnicodeSymbol	Decode (const char *&src)
	Convert sequence of UTF8 code units into Unicode code point.
static TUnicodeSymbol	DecodeFirst (char ch, SIZE_TYPE &more)
	Convert first character of UTF8 sequence into Unicode.
static TUnicodeSymbol	DecodeNext (TUnicodeSymbol chU, char ch)
	Convert next character of UTF8 sequence into Unicode.
Private Member Functions
string	AsAscii (void) const
	Function AsAscii is deprecated - use AsLatin1() instead.
template<typename TChar>
basic_string< TChar >	x_AsBasicString (const TChar *substitute_on_error) const
	Conversion to basic_string with any base type we need.
void	x_Validate (void) const
void	x_AppendChar (TUnicodeSymbol ch)
	Convert Unicode code point into UTF8 and append.
void	x_Append (const char *src, EEncoding encoding=eEncoding_ISO8859_1, EValidate validate=eNoValidate)
	Convert coded character sequence into UTF8 and append.
template<typename TChar>
void	x_Append (const TChar *src)
	Convert Unicode character sequence into UTF8 and append Sequence can be in UCS-4 (TChar == (U)Int4), UCS-2 (TChar == (U)Int2) or in ISO8859-1 (TChar == char).
Static Private Member Functions
static SIZE_TYPE	x_BytesNeeded (TUnicodeSymbol ch)
	Check how many bytes is needed to represent the code point in UTF8.
static bool	x_EvalFirst (char ch, SIZE_TYPE &more)
	Check if the character is valid first code unit of UTF8.
static bool	x_EvalNext (char ch)
	Check if the character is valid non-first code unit of UTF8.

CStringUTF8 Class Reference [String Manipulations]

Detailed Description

Public Types

Public Member Functions

Static Public Member Functions

Private Member Functions

Static Private Member Functions

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

CStringUTF8 Class Reference
[String Manipulations]