lib/unicase/u-prefix-context.h

   1 /* Case-mapping context of prefix UTF-8/UTF-16/UTF-32 string.
   2    Copyright (C) 2009-2019 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2009.
   4
   5    This program is free software: you can redistribute it and/or modify it
   6    under the terms of the GNU Lesser General Public License as published
   7    by the Free Software Foundation; either version 3 of the License, or
   8    (at your option) any later version.
   9
  10    This program 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 GNU
  13    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 casing_prefix_context_t
  19 FUNC1 (const UNIT *s, size_t n)
  20 {
  21   return FUNC2 (s, n, unicase_empty_prefix_context);
  22 }
  23
  24 casing_prefix_context_t
  25 FUNC2 (const UNIT *s, size_t n, casing_prefix_context_t a_context)
  26 {
  27 #if 0
  28   /* Forward iteration.  Slow for long strings.  */
  29   casing_prefix_context_t context = a_context;
  30   const UNIT *s_end = s + n;
  31
  32   while (s < s_end)
  33     {
  34       ucs4_t uc;
  35       int count = U_MBTOUC_UNSAFE (&uc, s, s_end - s);
  36
  37       if (!uc_is_case_ignorable (uc))
  38         context.last_char_except_ignorable = uc;
  39
  40       {
  41         int ccc = uc_combining_class (uc);
  42         if (ccc == UC_CCC_A || ccc == UC_CCC_NR)
  43           context.last_char_normal_or_above = uc;
  44       }
  45
  46       s += count;
  47     }
  48
  49   return context;
  50 #else
  51   /* Iterate backwards, only as far as needed.  */
  52   casing_prefix_context_t context;
  53   ucs4_t last_char_except_ignorable = (ucs4_t)(-1);
  54   ucs4_t last_char_normal_or_above = (ucs4_t)(-1);
  55   const UNIT *p = s + n;
  56
  57   for (;;)
  58     {
  59       ucs4_t uc;
  60       p = U_PREV (&uc, p, s);
  61       if (p == NULL)
  62         break;
  63
  64       if (last_char_except_ignorable == (ucs4_t)(-1))
  65         {
  66           if (!uc_is_case_ignorable (uc))
  67             last_char_except_ignorable = uc;
  68         }
  69
  70       if (last_char_normal_or_above == (ucs4_t)(-1))
  71         {
  72           int ccc = uc_combining_class (uc);
  73           if (ccc == UC_CCC_A || ccc == UC_CCC_NR)
  74             last_char_normal_or_above = uc;
  75         }
  76
  77       if (last_char_except_ignorable != (ucs4_t)(-1)
  78           && last_char_normal_or_above != (ucs4_t)(-1))
  79         break;
  80     }
  81   context.last_char_except_ignorable =
  82     (last_char_except_ignorable != (ucs4_t)(-1)
  83      ? last_char_except_ignorable
  84      : a_context.last_char_except_ignorable);
  85   context.last_char_normal_or_above =
  86     (last_char_normal_or_above != (ucs4_t)(-1)
  87      ? last_char_normal_or_above
  88      : a_context.last_char_normal_or_above);
  89
  90   return context;
  91 #endif
  92 }