1 /* $NetBSD: unicode.cpp,v 1.1.1.1 2016/01/13 18:41:48 christos Exp $ */
2
3 // -*- C++ -*-
4 /* Copyright (C) 2002
5 Free Software Foundation, Inc.
6 Written by Werner Lemberg <wl@gnu.org>
7
8 This file is part of groff.
9
10 groff is free software; you can redistribute it and/or modify it under
11 the terms of the GNU General Public License as published by the Free
12 Software Foundation; either version 2, or (at your option) any later
13 version.
14
15 groff is distributed in the hope that it will be useful, but WITHOUT ANY
16 WARRANTY; without even the implied warranty of MERCHANTABILITY or
17 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
18 for more details.
19
20 You should have received a copy of the GNU General Public License along
21 with groff; see the file COPYING. If not, write to the Free Software
22 Foundation, 51 Franklin St - Fifth Floor, Boston, MA 02110-1301, USA. */
23
24 #include "lib.h"
25 #include "cset.h"
26 #include "stringclass.h"
27
28 #include "unicode.h"
29
check_unicode_name(const char * u)30 const char *check_unicode_name(const char *u)
31 {
32 if (*u != 'u')
33 return 0;
34 const char *p = ++u;
35 for (;;) {
36 int val = 0;
37 const char *start = p;
38 for (;;) {
39 // only uppercase hex digits allowed
40 if (!csxdigit(*p))
41 return 0;
42 if (csdigit(*p))
43 val = val*0x10 + (*p-'0');
44 else if (csupper(*p))
45 val = val*0x10 + (*p-'A'+10);
46 else
47 return 0;
48 // biggest Unicode value is U+10FFFF
49 if (val > 0x10FFFF)
50 return 0;
51 p++;
52 if (*p == '\0' || *p == '_')
53 break;
54 }
55 // surrogates not allowed
56 if ((val >= 0xD800 && val <= 0xDBFF) || (val >= 0xDC00 && val <= 0xDFFF))
57 return 0;
58 if (val > 0xFFFF) {
59 if (*start == '0') // no leading zeros allowed if > 0xFFFF
60 return 0;
61 }
62 else if (p - start != 4) // otherwise, check for exactly 4 hex digits
63 return 0;
64 if (*p == '\0')
65 break;
66 p++;
67 }
68 return u;
69 }
70