lib/unicase/ignorable.c

   1 /* Test whether a Unicode character is case-ignorable.
   2    Copyright (C) 2002, 2006-2007, 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 #include <config.h>
  19
  20 /* Specification.  */
  21 #include "caseprop.h"
  22
  23 /* Quoting the Unicode standard:
  24      Definition: A character is defined to be "case-ignorable" if it has the
  25      value MidLetter {or the value MidNumLet} for the Word_Break property or
  26      its General_Category is one of Nonspacing_Mark (Mn), Enclosing_Mark (Me),
  27      Format (Cf), Modifier_Letter (Lm), or Modifier_Symbol (Sk).
  28    The text marked in braces was added in Unicode 5.1.0, see
  29    <http://www.unicode.org/versions/Unicode5.1.0/> section "Update of
  30    Definition of case-ignorable".   */
  31 /* Since this predicate is only used for the "Before C" and "After C"
  32    conditions of FINAL_SIGMA, we exclude the "cased" characters here.
  33    This simplifies the evaluation of the regular expressions
  34      \p{cased} (\p{case-ignorable})* C
  35    and
  36      C (\p{case-ignorable})* \p{cased}
  37  */
  38
  39 #if 0
  40
  41 #include "unictype.h"
  42 #include "uniwbrk.h"
  43
  44 bool
  45 uc_is_case_ignorable (ucs4_t uc)
  46 {
  47   int wbp = uc_wordbreak_property (uc);
  48
  49   return (wbp == WBP_MIDLETTER || wbp == WBP_MIDNUMLET
  50           || uc_is_general_category_withtable (uc, UC_CATEGORY_MASK_Mn
  51                                                    | UC_CATEGORY_MASK_Me
  52                                                    | UC_CATEGORY_MASK_Cf
  53                                                    | UC_CATEGORY_MASK_Lm
  54                                                    | UC_CATEGORY_MASK_Sk))
  55          && !uc_is_cased (uc);
  56 }
  57
  58 #else
  59
  60 #include "unictype/bitmap.h"
  61
  62 /* Define u_casing_property_case_ignorable table.  */
  63 #include "ignorable.h"
  64
  65 bool
  66 uc_is_case_ignorable (ucs4_t uc)
  67 {
  68   return bitmap_lookup (&u_casing_property_case_ignorable, uc);
  69 }
  70
  71 #endif