src/libs/libgroff/unicode.cpp

   1 // -*- C++ -*-
   2 /* Copyright (C) 2002
   3    Free Software Foundation, Inc.
   4      Written by Werner Lemberg <wl@gnu.org>
   5
   6 This file is part of groff.
   7
   8 groff is free software; you can redistribute it and/or modify it under
   9 the terms of the GNU General Public License as published by the Free
  10 Software Foundation; either version 2, or (at your option) any later
  11 version.
  12
  13 groff is distributed in the hope that it will be useful, but WITHOUT ANY
  14 WARRANTY; without even the implied warranty of MERCHANTABILITY or
  15 FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  16 for more details.
  17
  18 You should have received a copy of the GNU General Public License along
  19 with groff; see the file COPYING.  If not, write to the Free Software
  20 Foundation, 51 Franklin St - Fifth Floor, Boston, MA 02110-1301, USA. */
  21
  22 #include "lib.h"
  23 #include "cset.h"
  24 #include "stringclass.h"
  25
  26 #include "unicode.h"
  27
  28 const char *check_unicode_name(const char *u)
  29 {
  30   if (*u != 'u')
  31     return 0;
  32   const char *p = ++u;
  33   for (;;) {
  34     int val = 0;
  35     const char *start = p;
  36     for (;;) {
  37       // only uppercase hex digits allowed
  38       if (!csxdigit(*p))
  39         return 0;
  40       if (csdigit(*p))
  41         val = val*0x10 + (*p-'0');
  42       else if (csupper(*p))
  43         val = val*0x10 + (*p-'A'+10);
  44       else
  45         return 0;
  46       // biggest Unicode value is U+10FFFF
  47       if (val > 0x10FFFF)
  48         return 0;
  49       p++;
  50       if (*p == '\0' || *p == '_')
  51         break;
  52     }
  53     // surrogates not allowed
  54     if ((val >= 0xD800 && val <= 0xDBFF) || (val >= 0xDC00 && val <= 0xDFFF))
  55       return 0;
  56     if (val > 0xFFFF) {
  57       if (*start == '0')        // no leading zeros allowed if > 0xFFFF
  58         return 0;
  59     }
  60     else if (p - start != 4)    // otherwise, check for exactly 4 hex digits
  61       return 0;
  62     if (*p == '\0')
  63       break;
  64     p++;
  65   }
  66   return u;
  67 }