chartype.h revision 1.17 
1/*	$OpenBSD: chartype.h,v 1.17 2016/04/11 20:43:33 schwarze Exp $	*/
2/*	$NetBSD: chartype.h,v 1.5 2010/04/15 00:55:57 christos Exp $	*/
3
4/*-
5 * Copyright (c) 2009 The NetBSD Foundation, Inc.
6 * All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
18 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
19 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
20 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
21 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
22 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
23 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
24 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
25 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
26 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
27 * POSSIBILITY OF SUCH DAMAGE.
28 */
29
30#ifndef _h_chartype_f
31#define _h_chartype_f
32
33#ifndef NARROWCHAR
34
35/* Ideally we should also test the value of the define to see if it
36 * supports non-BMP code points without requiring UTF-16, but nothing
37 * seems to actually advertise this properly, despite Unicode 3.1 having
38 * been around since 2001... */
39#if !defined(__NetBSD__) && !defined(__OpenBSD__)
40#ifndef __STDC_ISO_10646__
41/* In many places it is assumed that the first 127 code points are ASCII
42 * compatible, so ensure wchar_t indeed does ISO 10646 and not some other
43 * funky encoding that could break us in weird and wonderful ways. */
44	#error wchar_t must store ISO 10646 characters
45#endif
46#endif
47
48/* Oh for a <uchar.h> with char32_t and __STDC_UTF_32__ in it...
49 * ref: ISO/IEC DTR 19769
50 */
51#if WCHAR_MAX < INT32_MAX
52#warning Build environment does not support non-BMP characters
53#endif
54
55/*
56 * Conversion buffer
57 */
58typedef struct ct_buffer_t {
59        char    *cbuff;
60        size_t  csize;
61        wchar_t *wbuff;
62        size_t  wsize;
63} ct_buffer_t;
64
65#define ct_encode_string __ct_encode_string
66/* Encode a wide-character string and return the UTF-8 encoded result. */
67public char *ct_encode_string(const wchar_t *, ct_buffer_t *);
68
69#define ct_decode_string __ct_decode_string
70/* Decode a (multi)?byte string and return the wide-character string result. */
71public wchar_t *ct_decode_string(const char *, ct_buffer_t *);
72
73/* Decode a (multi)?byte argv string array.
74 * The pointer returned must be free()d when done. */
75protected wchar_t **ct_decode_argv(int, const char *[],  ct_buffer_t *);
76
77/* Resizes the conversion buffer(s) if needed. */
78protected void ct_conv_buff_resize(ct_buffer_t *, size_t, size_t);
79protected ssize_t ct_encode_char(char *, size_t, wchar_t);
80protected size_t ct_enc_width(wchar_t);
81
82#else
83#define	ct_encode_string(s, b)	(s)
84#define ct_decode_string(s, b)	(s)
85#endif
86
87#ifndef NARROWCHAR
88/* Encode a characted into the destination buffer, provided there is sufficent
89 * buffer space available. Returns the number of bytes used up (zero if the
90 * character cannot be encoded, -1 if there was not enough space available). */
91
92/* The maximum buffer size to hold the most unwieldly visual representation,
93 * in this case \U+nnnnn. */
94#define VISUAL_WIDTH_MAX 8
95
96/* The terminal is thought of in terms of X columns by Y lines. In the cases
97 * where a wide character takes up more than one column, the adjacent
98 * occupied column entries will contain this faux character. */
99#define MB_FILL_CHAR ((wchar_t)-1)
100
101/* Visual width of character c, taking into account ^? , \0177 and \U+nnnnn
102 * style visual expansions. */
103protected int ct_visual_width(wchar_t);
104
105/* Turn the given character into the appropriate visual format, matching
106 * the width given by ct_visual_width(). Returns the number of characters used
107 * up, or -1 if insufficient space. Buffer length is in count of wchar_t's. */
108protected ssize_t ct_visual_char(wchar_t *, size_t, wchar_t);
109
110/* Convert the given string into visual format, using the ct_visual_char()
111 * function. Uses a static buffer, so not threadsafe. */
112protected const wchar_t *ct_visual_string(const wchar_t *);
113
114
115/* printable character, use ct_visual_width() to find out display width */
116#define CHTYPE_PRINT        ( 0)
117/* control character found inside the ASCII portion of the charset */
118#define CHTYPE_ASCIICTL     (-1)
119/* a \t */
120#define CHTYPE_TAB          (-2)
121/* a \n */
122#define CHTYPE_NL           (-3)
123/* non-printable character */
124#define CHTYPE_NONPRINT     (-4)
125/* classification of character c, as one of the above defines */
126protected int ct_chr_class(wchar_t c);
127#endif
128
129#endif /* _chartype_f */
130