unicode.cc File Reference

#include "unicode.hh"
#include "blob.hh"
#include "platform.hh"
#include "websocket.hh"
#include <glib.h>
#include "testing.hh"
#include "internal.hh"

Go to the source code of this file.

Namespaces
namespace	Ase
	The Anklang C++ API namespace.

Functions
std::string	Ase::encodefs (const std::string &fschars)
	Encode a file system path consisting of bytes into UTF-8, using surrogate code points to store non UTF-8 bytes.
std::string	Ase::decodefs (const std::string &utf8str)
	Decode UTF-8 string back into file system path representation, extracting surrogate code points as bytes.
std::string	Ase::displayfs (const std::string &utf8str)
	Convert UTF-8 encoded file system path into human readable display format, the conversion is lossy but readable.
size_t	Ase::utf8len (const char *str)
	Count valid UTF-8 sequences, invalid sequences are counted as Latin-1 characters.
size_t	Ase::utf8len (const std::string &str)
	Count valid UTF-8 sequences, invalid sequences are counted as Latin-1 characters.
std::vector< uint32_t >	Ase::utf8decode (const std::string &utf8str)
	Convert valid UTF-8 sequences to Unicode codepoints, invalid sequences are treated as Latin-1 characters.
size_t	Ase::utf8_to_unicode (const char *str, uint32_t *codepoints)
size_t	Ase::utf8_to_unicode (const std::string &str, std::vector< uint32_t > &codepoints)
std::string	Ase::utf8encode (const uint32_t *codepoints, size_t n_codepoints)
	Convert codepoints into an UTF-8 string, using the shortest possible encoding.
std::string	Ase::utf8encode (const std::vector< uint32_t > &codepoints)
	Convert codepoints into an UTF-8 string, using the shortest possible encoding.
bool	Ase::string_is_ncname (const String &input)
String	Ase::string_to_ncname (const String &input, uint32_t substitute)