lib/uninorm/decomposition-table.h

   1 /* Decomposition of Unicode characters.
   2    Copyright (C) 2001-2003, 2009-2024 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2009.
   4
   5    This file is free software: you can redistribute it and/or modify
   6    it under the terms of the GNU Lesser General Public License as
   7    published by the Free Software Foundation; either version 2.1 of the
   8    License, or (at your option) any later version.
   9
  10    This file is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13    GNU Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public License
  16    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  17
  18
  19 #include "unitypes.h"
  20
  21 /* The decomposition table is made of two parts:
  22      - A table containing the actual arrays of decomposed equivalents.
  23        (This table is separate because the maximum length of a decomposition
  24        is 18, much larger than the average length 1.497 of a decomposition).
  25      - A 3-level table of indices into this array.  */
  26
  27 #include "decomposition-table1.h"
  28
  29 static inline unsigned short
  30 decomp_index (ucs4_t uc)
  31 {
  32   unsigned int index1 = uc >> decomp_header_0;
  33   if (index1 < decomp_header_1)
  34     {
  35       int lookup1 = gl_uninorm_decomp_index_table.level1[index1];
  36       if (lookup1 >= 0)
  37         {
  38           unsigned int index2 = (uc >> decomp_header_2) & decomp_header_3;
  39           int lookup2 = gl_uninorm_decomp_index_table.level2[lookup1 + index2];
  40           if (lookup2 >= 0)
  41             {
  42               unsigned int index3 = uc & decomp_header_4;
  43               return gl_uninorm_decomp_index_table.level3[lookup2 + index3];
  44             }
  45         }
  46     }
  47   return (unsigned short)(-1);
  48 }