Line data    Source code

       1             : /* src/toolbox/utf16_transform.inc - implementation of utf16 encoder
       2             : 
       3             :    Copyright (C) 1996-2013
       4             :    CACAOVM - Verein zur Foerderung der freien virtuellen Maschine CACAO
       5             : 
       6             :    This file is part of CACAO.
       7             : 
       8             :    This program is free software; you can redistribute it and/or
       9             :    modify it under the terms of the GNU General Public License as
      10             :    published by the Free Software Foundation; either version 2, or (at
      11             :    your option) any later version.
      12             : 
      13             :    This program is distributed in the hope that it will be useful, but
      14             :    WITHOUT ANY WARRANTY; without even the implied warranty of
      15             :    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
      16             :    General Public License for more details.
      17             : 
      18             :    You should have received a copy of the GNU General Public License
      19             :    along with this program; if not, write to the Free Software
      20             :    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
      21             :    02110-1301, USA.
      22             : 
      23             : */
      24             : 
      25             : #ifndef UTF16_TRANSFORM_INC
      26             : #define UTF16_TRANSFORM_INC 1
      27             : 
      28             : namespace utf16 {
      29             : 
      30             : namespace impl {
      31             :         struct CopyUtf16ToUtf8 : utf8::VisitorBase<void, utf8::IGNORE_ERRORS> {
      32             :                 typedef void ReturnType;
      33             : 
      34        1997 :                 CopyUtf16ToUtf8(char *dst) : dst(dst) {}
      35             : 
      36      161440 :                 void utf8(uint8_t c) { *dst++ = c; }
      37             : 
      38        1997 :                 void finish() { *dst = '\0'; }
      39             :         private:
      40             :                 char *dst;
      41             :         };
      42             : } // end namespace impl
      43             : 
      44             :         template<typename Iterator, typename Fn>
      45       26881 :         inline typename Fn::ReturnType transform(Iterator it, Iterator end, Fn fn) {
      46      811447 :                 for (; it != end; ++it) {
      47      784566 :                         uint16_t c = *it;
      48             : 
      49      784566 :                         fn.utf16(c);
      50             : 
      51     1569132 :                         if ((c != 0) && (c < 0x80)) {
      52             :                                 // 1 character
      53      784566 :                                 fn.utf8((char) c);
      54           0 :                         } else if (c < 0x800) {
      55             :                                 // 2 characters
      56           0 :                         unsigned char high = c >> 6;
      57           0 :                         unsigned char low  = c & 0x3F;
      58             : 
      59           0 :                                 fn.utf8(high | 0xC0);
      60           0 :                                 fn.utf8(low  | 0x80);
      61             :                         } else {
      62             :                         // 3 characters
      63           0 :                         char low  = c & 0x3f;
      64           0 :                         char mid  = (c >> 6) & 0x3F;
      65           0 :                         char high = c >> 12;
      66             : 
      67           0 :                                 fn.utf8(high | 0xE0);
      68           0 :                                 fn.utf8(mid  | 0x80);
      69           0 :                                 fn.utf8(low  | 0x80);
      70             :                         }
      71             :                 }
      72             : 
      73       26881 :                 return fn.finish();
      74             :         }
      75             : 
      76             : 
      77             :         template<typename Utf16Iterator>
      78        1997 :         inline void encode(Utf16Iterator begin, Utf16Iterator end, char *dst) {
      79        1997 :                 ::utf16::transform(begin, end, ::utf16::impl::CopyUtf16ToUtf8(dst));
      80        1997 :         }
      81             : 
      82             : } // end namespace utf16
      83             : 
      84             : 
      85             : #endif // UTF16_TRANSFORM_INC
      86             : 
      87             : /*
      88             :  * These are local overrides for various environment variables in Emacs.
      89             :  * Please do not remove this and leave it at the end of the file, where
      90             :  * Emacs will automagically detect them.
      91             :  * ---------------------------------------------------------------------
      92             :  * Local variables:
      93             :  * mode: c++
      94             :  * indent-tabs-mode: t
      95             :  * c-basic-offset: 4
      96             :  * tab-width: 4
      97             :  * End:
      98             :  * vim:noexpandtab:sw=4:ts=4:
      99             :  */