utf8.cpp File Reference

#include "utf8.h"
#include <limits>
#include <cstdint>
#include <string>
#include <vector>
#include <cstdlib>

Namespaces
	gnash
	Anonymous namespace for callbacks, local functions, event handlers etc.
	gnash::utf8
	Utilities to convert between std::string and std::wstring.

Macros
#define	FIRST_BYTE(mask, shift)
#define	NEXT_BYTE(shift)
#define	ENC_DEFAULT   0
#define	ENC_UTF8   1
#define	ENC_UTF16BE   2
#define	ENC_UTF16LE   3

Functions
std::wstring	gnash::utf8::decodeCanonicalString (const std::string &str, int version)
	Converts a std::string with multibyte characters into a std::wstring. More...
std::string	gnash::utf8::encodeCanonicalString (const std::wstring &wstr, int version)
	Converts a std::wstring into canonical std::string. More...
std::string	gnash::utf8::encodeLatin1Character (std::uint32_t ucsCharacter)
	Encodes the given wide character into an at least 8-bit character. More...
std::uint32_t	gnash::utf8::decodeNextUnicodeCharacter (std::string::const_iterator &it, const std::string::const_iterator &e)
	Return the next Unicode character in the UTF-8 encoded string. More...
std::string	gnash::utf8::encodeUnicodeCharacter (std::uint32_t ucs_character)
	Encodes the given wide character into a canonical string, theoretically up to 6 chars in length. More...
const char *	gnash::utf8::stripBOM (const char *in, size_t &size, TextEncoding &encoding)
	Interpret (and skip) Byte Order Mark in input stream. More...
const char *	gnash::utf8::textEncodingName (TextEncoding enc)
	Return name of a text encoding. More...
EncodingGuess	gnash::utf8::guessEncoding (const std::string &s, int &length, std::vector< int > &offsets)
	Common code for guessing at the encoding of random text, between. More...

Macro Definition Documentation

ENC_DEFAULT

#define ENC_DEFAULT   0

ENC_UTF16BE

#define ENC_UTF16BE   2

ENC_UTF16LE

#define ENC_UTF16LE   3

ENC_UTF8

#define ENC_UTF8   1

FIRST_BYTE

#define FIRST_BYTE	(		mask,
			shift
	)

Value:

/* Post-increment iterator */ \
    uc = (*it++ & (mask)) << (shift);

Referenced by gnash::utf8::decodeNextUnicodeCharacter().

NEXT_BYTE

#define NEXT_BYTE

(

shift

)

Value:

\
    if (it == e || *it == 0) return 0; /* end of buffer, do not advance */    \
    if ((*it & 0xC0) != 0x80) return invalid; /* standard check */    \
    /* Post-increment iterator: */        \
    uc |= (*it++ & 0x3F) << shift;

Referenced by gnash::utf8::decodeNextUnicodeCharacter().