lib/unicase/u-suffix-context.h

   1 /* Case-mapping context of suffix UTF-8/UTF-16/UTF-32 string.
   2    Copyright (C) 2009-2021 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_suffix_context_t
  19 FUNC1 (const UNIT *s, size_t n)
  20 {
  21   return FUNC2 (s, n, unicase_empty_suffix_context);
  22 }
  23
  24 casing_suffix_context_t
  25 FUNC2 (const UNIT *s, size_t n, casing_suffix_context_t a_context)
  26 {
  27   casing_suffix_context_t context;
  28   /* Evaluate all three conditions in a single pass through the string S.
  29      The three variables are -1 as long as the value of the condition has
  30      not been determined.  */
  31   ucs4_t first_char_except_ignorable = (ucs4_t)(-1);
  32   int scc_MORE_ABOVE = -1;
  33   int scc_BEFORE_DOT = -1;
  34   const UNIT *s_end = s + n;
  35
  36   while (s < s_end)
  37     {
  38       ucs4_t uc;
  39       int count = U_MBTOUC_UNSAFE (&uc, s, s_end - s);
  40
  41       if (first_char_except_ignorable == (ucs4_t)(-1))
  42         {
  43           if (!uc_is_case_ignorable (uc))
  44             first_char_except_ignorable = uc;
  45         }
  46
  47       if (scc_MORE_ABOVE < 0)
  48         {
  49           int ccc = uc_combining_class (uc);
  50           if (ccc == UC_CCC_A)
  51             scc_MORE_ABOVE = SCC_MORE_ABOVE_MASK;
  52           else if (ccc == UC_CCC_NR)
  53             scc_MORE_ABOVE = 0;
  54         }
  55
  56       if (scc_BEFORE_DOT < 0)
  57         {
  58           if (uc == 0x0307) /* COMBINING DOT ABOVE */
  59             scc_BEFORE_DOT = SCC_BEFORE_DOT_MASK;
  60           else
  61             {
  62               int ccc = uc_combining_class (uc);
  63               if (ccc == UC_CCC_A || ccc == UC_CCC_NR)
  64                 scc_BEFORE_DOT = 0;
  65             }
  66         }
  67
  68       if (first_char_except_ignorable != (ucs4_t)(-1)
  69           && (scc_MORE_ABOVE | scc_BEFORE_DOT) >= 0)
  70         /* All conditions have been determined.  */
  71         break;
  72
  73       s += count;
  74     }
  75
  76   /* For those conditions that have not been determined so far, use the
  77      value from the argument context.  */
  78   context.first_char_except_ignorable =
  79     (first_char_except_ignorable != (ucs4_t)(-1)
  80      ? first_char_except_ignorable
  81      : a_context.first_char_except_ignorable);
  82   context.bits =
  83     (scc_MORE_ABOVE >= 0
  84      ? scc_MORE_ABOVE
  85      : a_context.bits & SCC_MORE_ABOVE_MASK)
  86     | (scc_BEFORE_DOT >= 0
  87        ? scc_BEFORE_DOT
  88        : a_context.bits & SCC_BEFORE_DOT_MASK);
  89   return context;
  90 }