lib/unicase/u-ct-casefold.h

   1 /* Casefolding mapping for Unicode substrings (locale dependent).
   2    Copyright (C) 2009-2020 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 UNIT *
  19 FUNC (const UNIT *s, size_t n,
  20       casing_prefix_context_t prefix_context,
  21       casing_suffix_context_t suffix_context,
  22       const char *iso639_language,
  23       uninorm_t nf,
  24       UNIT *resultbuf, size_t *lengthp)
  25 {
  26   /* Implement the three definitions of caseless matching, as described in
  27      Unicode 5.0, section "Default caseless matching":
  28        - If no normalization is requested, simply apply the casefolding.
  29            X -> toCasefold(X).
  30        - If canonical normalization is requested, apply it, and apply an NFD
  31          before.
  32            X -> NFD(toCasefold(NFD(X))).
  33        - If compatibility normalization is requested, apply it twice, apply
  34          the normalization after each, and apply an NFD before:
  35            X -> NFKD(toCasefold(NFKD(toCasefold(NFD(X))))).  */
  36   if (nf == NULL)
  37     /* X -> toCasefold(X) */
  38     return U_CASEMAP (s, n, prefix_context, suffix_context, iso639_language,
  39                       uc_tocasefold, offsetof (struct special_casing_rule, casefold[0]),
  40                       NULL,
  41                       resultbuf, lengthp);
  42   else
  43     {
  44       uninorm_t nfd = uninorm_decomposing_form (nf);
  45       /* X -> nf(toCasefold(NFD(X))) or
  46          X -> nf(toCasefold(nfd(toCasefold(NFD(X)))))  */
  47       int repeat = (uninorm_is_compat_decomposing (nf) ? 2 : 1);
  48       UNIT tmpbuf1[2048 / sizeof (UNIT)];
  49       UNIT tmpbuf2[2048 / sizeof (UNIT)];
  50       UNIT *tmp1;
  51       size_t tmp1_length;
  52       UNIT *tmp2;
  53       size_t tmp2_length;
  54
  55       tmp1_length = sizeof (tmpbuf1) / sizeof (UNIT);
  56       tmp1 = U_NORMALIZE (UNINORM_NFD, s, n, tmpbuf1, &tmp1_length);
  57       if (tmp1 == NULL)
  58         /* errno is set here.  */
  59         return NULL;
  60
  61       do
  62         {
  63           tmp2_length = sizeof (tmpbuf2) / sizeof (UNIT);
  64           tmp2 = U_CASEMAP (tmp1, tmp1_length,
  65                             prefix_context, suffix_context, iso639_language,
  66                             uc_tocasefold, offsetof (struct special_casing_rule, casefold[0]),
  67                             NULL,
  68                             tmpbuf2, &tmp2_length);
  69           if (tmp2 == NULL)
  70             {
  71               int saved_errno = errno;
  72               if (tmp1 != tmpbuf1)
  73                 free (tmp1);
  74               errno = saved_errno;
  75               return NULL;
  76             }
  77
  78           if (tmp1 != tmpbuf1)
  79             free (tmp1);
  80
  81           if (repeat > 1)
  82             {
  83               tmp1_length = sizeof (tmpbuf1) / sizeof (UNIT);
  84               tmp1 = U_NORMALIZE (nfd, tmp2, tmp2_length,
  85                                   tmpbuf1, &tmp1_length);
  86             }
  87           else
  88             /* Last run through this loop.  */
  89             tmp1 = U_NORMALIZE (nf, tmp2, tmp2_length,
  90                                 resultbuf, lengthp);
  91           if (tmp1 == NULL)
  92             {
  93               int saved_errno = errno;
  94               if (tmp2 != tmpbuf2)
  95                 free (tmp2);
  96               errno = saved_errno;
  97               return NULL;
  98             }
  99
 100           if (tmp2 != tmpbuf2)
 101             free (tmp2);
 102         }
 103       while (--repeat > 0);
 104
 105       return tmp1;
 106     }
 107 }