/** * \file unicode.h * This file is part of LyX, the document processor. * Licence details can be found in the file COPYING. * * \author Lars Gullik Bjønnes * * Full author contact details are available in file CREDITS. * * A collection of unicode conversion functions, using iconv. */ #ifndef LYX_SUPPORT_UNICODE_H #define LYX_SUPPORT_UNICODE_H #include "support/types.h" #include #include #include namespace lyx { class IconvProcessor { public: IconvProcessor( char const * tocode = "", char const * fromcode = ""); /// copy constructor needed because of pimpl_ IconvProcessor(IconvProcessor const &); /// assignment operator needed because of pimpl_ IconvProcessor & operator=(IconvProcessor const &); /// destructor (needs to be implemented in the .C file because the /// boost::scoped_ptr destructor needs a fully defined type ~IconvProcessor(); /// convert any data from \c fromcode to \c tocode unicode format. /// \return the number of bytes of the converted output buffer. int convert( char const * in_buffer, size_t in_size, char * out_buffer, size_t max_out_size); private: /// open iconv. /// \return true if the processor is ready to use. bool init(); std::string tocode_; std::string fromcode_; struct Private; boost::scoped_ptr pimpl_; }; // A single codepoint conversion for utf8_to_ucs4 does not make // sense, so that function is left out. std::vector utf8_to_ucs4(std::vector const & utf8str); std::vector utf8_to_ucs4(char const * utf8str, size_t ls); // utf16_to_ucs4 std::vector utf16_to_ucs4(unsigned short const * s, size_t ls); // ucs4_to_utf16 std::vector ucs4_to_utf16(char_type const * s, size_t ls); // ucs4_to_utf8 std::vector ucs4_to_utf8(char_type c); std::vector ucs4_to_utf8(std::vector const & ucs4str); std::vector ucs4_to_utf8(char_type const * ucs4str, size_t ls); /// convert \p s from encoding \p encoding to ucs4. /// \p encoding must be a valid iconv 8bit encoding std::vector eightbit_to_ucs4(char const * s, size_t ls, std::string const & encoding); /// convert \p s from ucs4 to encoding \p encoding. /// \p encoding must be a valid iconv 8bit encoding std::vector ucs4_to_eightbit(char_type const * ucs4str, size_t ls, std::string const & encoding); /// convert ucs4 character \p c to encoding \p encoding. /// \p encoding must be a valid iconv 8bit encoding char ucs4_to_eightbit(char_type c, std::string const & encoding); /// void ucs4_to_multibytes(char_type ucs4, std::vector & out, std::string const & encoding); extern char const * ucs4_codeset; } // namespace lyx #endif