UTF8String Class Reference

#include <Utf8String.h>

List of all members.

Public Member Functions
	UTF8String ()
	UTF8String (const std::string &s)
	UTF8String (const UTF8String &s)
unsigned int	unicodeValueCount () const
UTF8String	unicodeSubString (unsigned int stt, unsigned int howManyCharacters=0) const
UTF8String	operator[] (unsigned int pos) const
UTF32	unicodeValueAtPosition (unsigned int pos=0) const
bool	isRTL (void) const
bool	isIndic (void) const
bool	isArabic (void) const
SCRIPTCODE	getScriptCode (void)
std::basic_string< UTF32 >	UTF32String () const
UTF8String &	append (const std::basic_string< UTF32 > &UTF32String)
UTF8String &	append (const std::basic_string< UTF16 > &UTF16String)
UTF8String &	operator+= (const std::basic_string< UTF32 > &UTF32String)
UTF8String &	operator+= (const std::basic_string< UTF16 > &UTF16String)
UTF8String &	operator= (const std::basic_string< UTF32 > &UTF32String)
UTF8String &	operator= (const std::basic_string< UTF16 > &UTF16String)
	UTF8String (const std::basic_string< UTF32 > &UTF32String)
	UTF8String (const std::basic_string< UTF16 > &UTF16String)
Private Member Functions
const char *	_UTF32ValueToUTF8 (UTF32 UTF32Value)

---

Constructor & Destructor Documentation

UTF8String::UTF8String (   )

UTF8String::UTF8String (  const std::string &  s  )

UTF8String::UTF8String (  const UTF8String &  s  )

UTF8String::UTF8String (  const std::basic_string< UTF32 > &  UTF32String  )

UTF8String::UTF8String (  const std::basic_string< UTF16 > &  UTF16String  )

---

Member Function Documentation

const char * UTF8String::_UTF32ValueToUTF8 (  UTF32  UTF32Value  )  [private]

UTF8String & UTF8String::append (  const std::basic_string< UTF16 > &  UTF16String  )

UTF8String & UTF8String::append (  const std::basic_string< UTF32 > &  UTF32String  )

SCRIPTCODE UTF8String::getScriptCode (  void   )

getScriptCode(): Returns a script code based on the first character in the string:

bool UTF8String::isArabic (  void   )  const

isArabic() Returns true if the string starts with a Unicode character from Arabic

bool UTF8String::isIndic (  void   )  const

isIndic() Returns true if the string starts with a Unicode character from an Indic or Indic-derived script

bool UTF8String::isRTL (  void   )  const

isRTL() Returns true if the string starts with a Unicode character from a script that is written right-to-left.

UTF8String & UTF8String::operator+= (  const std::basic_string< UTF16 > &  UTF16String  )

UTF8String & UTF8String::operator+= (  const std::basic_string< UTF32 > &  UTF32String  )

UTF8String & UTF8String::operator= (  const std::basic_string< UTF16 > &  UTF16String  )

UTF8String & UTF8String::operator= (  const std::basic_string< UTF32 > &  UTF32String  )

UTF8String UTF8String::operator[] (  unsigned int  pos  )  const

UTF8String UTF8String::unicodeSubString (  unsigned int  stt, unsigned int  howManyCharacters = 0 )  const

UTF32 UTF8String::unicodeValueAtPosition (  unsigned int  pos = 0  )  const

unicodeValueAtPosition(): Note: The code in this method was inspired by a UTF8ToUTF32 method in the GPL'ed swunicod.cpp (c) 1998 by the CrossWire Bible Society (http://www.crosswire.org). It differs a bit from the method presented by the Unicode Consortium which relies on some static lookup-tables.

unsigned int UTF8String::unicodeValueCount (   )  const

unicodeValueCount() This function tells you the "length" of a UTF8 string in terms of the number of Unicode code points (values) encoded in the UTF-8 string. Since all UTF-8 continuation bytes have the pattern "10xxxxxx" (hence the mask 0x00C0), counting only those bytes that are not continuation bytes (hence "!=0x0080) directly provides the number of encoded code points:

std::basic_string< UTF32 > UTF8String::UTF32String (   )  const

UTF32String(): Converts a UTF8String to a UTF32String

---

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

• Utf8String.h
• Utf8String.cpp

---