The R Project SVN R

Rev

Rev 70788 | Rev 79676 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 70788 Rev 72707
Line 1... Line 1...
1 
/*
 1 
/*
2 
 *  R : A Computer Language for Statistical Data Analysis
 2 
 *  R : A Computer Language for Statistical Data Analysis
3 
 *  Copyright (C) 2005-2016   The R Core Team
 3 
 *  Copyright (C) 2005-2017   The R Core Team
4 
 *
 4 
 *
5 
 *  This program is free software; you can redistribute it and/or modify
 5 
 *  This program is free software; you can redistribute it and/or modify
6 
 *  it under the terms of the GNU General Public License as published by
 6 
 *  it under the terms of the GNU General Public License as published by
7 
 *  the Free Software Foundation; either version 2 of the License, or
 7 
 *  the Free Software Foundation; either version 2 of the License, or
8 
 *  (at your option) any later version.
 8 
 *  (at your option) any later version.
Line 37... Line 37...
37 
#include <wchar.h>
 37 
#include <wchar.h>
38 
#include <ctype.h>
 38 
#include <ctype.h>
39 
#include <wctype.h>
 39 
#include <wctype.h>
40 
 
 40 
 
41 
/*
 41 
/*
- 
 
 42 
 * The Rwchar_t typedef represents a single Unicode code point.  On most systems it's the same
- 
 
 43 
 * as wchar_t, but on Windows (and others?) where wchar_t is too small and UTF-16 is used,
- 
 
 44 
 * it is an unsigned int instead.
- 
 
 45 
 */
- 
 
 46
- 
 
 47 
#ifdef Win32
- 
 
 48 
typedef unsigned int Rwchar_t;
- 
 
 49 
#else
- 
 
 50 
typedef wchar_t Rwchar_t;
- 
 
 51 
#endif
- 
 
 52 
 
- 
 
 53 
/*
42 
 * Windows CJK
 54 
 * Windows CJK
43 
 * In Unicode, there is not a rule about character width.
55 
 * In Unicode, there is not a rule about character width.
44 
 * A letter of breadth is used in a CJK (China, Japan, Korea,
 56 
 * A letter of breadth is used in a CJK (China, Japan, Korea,
45 
 * Taiwan, Hong Kong, and Singapore) area, and there are a
 57 
 * Taiwan, Hong Kong, and Singapore) area, and there are a
46 
 * letter and a standard (character width is not still prescribed)
 58 
 * letter and a standard (character width is not still prescribed)
Line 64... Line 76...
64 
 *
 76 
 *
65 
 * The differences are mainly (but not exclusively) in the
 77 
 * The differences are mainly (but not exclusively) in the
66 
 * Unicode 'East Asian Ambiguous' class.
 78 
 * Unicode 'East Asian Ambiguous' class.
67 
 *
 79 
 *
68 
 */
 80 
 */
- 
 
 81
69 
extern int Ri18n_wcwidth(wchar_t);
 82 
extern int Ri18n_wcwidth(Rwchar_t);
70 
extern int Ri18n_wcswidth (const wchar_t *, size_t);
 83 
extern int Ri18n_wcswidth (const wchar_t *, size_t);
71 
 
 84 
 
72 
/* macOS CJK and WindowXP(Japanese)
 85 
/* macOS CJK and WindowXP(Japanese)
73 
 * iswctypes of macOS calls isctypes. no i18n.
 86 
 * iswctypes of macOS calls isctypes. no i18n.
74 
 * For example, iswprint of Windows does not accept a macron of
 87 
 * For example, iswprint of Windows does not accept a macron of
Line 112... Line 125...
112 
#define iswalnum(__x)     Ri18n_iswctype(__x, Ri18n_wctype("alnum"))
 125 
#define iswalnum(__x)     Ri18n_iswctype(__x, Ri18n_wctype("alnum"))
113 
#define wctype(__x)       Ri18n_wctype(__x)
 126 
#define wctype(__x)       Ri18n_wctype(__x)
114 
#define iswctype(__x,__y) Ri18n_iswctype(__x,__y)
 127 
#define iswctype(__x,__y) Ri18n_iswctype(__x,__y)
115 
#endif
 128 
#endif
116 
 
 129 
 
- 
 
 130 
/* These definitions are from winnls.h in Mingw_w64.  We don't need the rest of that file. */
- 
 
 131 
 
- 
 
 132 
#define HIGH_SURROGATE_START 0xd800
- 
 
 133 
#define HIGH_SURROGATE_END 0xdbff
- 
 
 134 
#define LOW_SURROGATE_START 0xdc00
- 
 
 135 
#define LOW_SURROGATE_END 0xdfff
- 
 
 136 
 
- 
 
 137 
/* The first two of these definitions use the argument twice which is bad, but we include them here in
- 
 
 138 
 * the original form for consistency with Mingw_w64.  Users should be careful that evaluating
- 
 
 139 
 * the argument doesn't result in side effects.
- 
 
 140 
 */
- 
 
 141 
 
- 
 
 142 
#define IS_HIGH_SURROGATE(wch) (((wch) >= HIGH_SURROGATE_START) && ((wch) <= HIGH_SURROGATE_END))
- 
 
 143 
#define IS_LOW_SURROGATE(wch) (((wch) >= LOW_SURROGATE_START) && ((wch) <= LOW_SURROGATE_END))
- 
 
 144 
#define IS_SURROGATE_PAIR(hs, ls) (IS_HIGH_SURROGATE (hs) && IS_LOW_SURROGATE (ls))
- 
 
 145 
 
- 
 
 146 
# define utf8toucs32		Rf_utf8toucs32
- 
 
 147 
Rwchar_t utf8toucs32(wchar_t high, const char *s);
- 
 
 148 
 
117 
#endif /* R_LOCALE_H */
 149 
#endif /* R_LOCALE_H */