chartype.h revision 1.9 
1/*	$OpenBSD: chartype.h,v 1.9 2016/03/20 20:35:38 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 * 3. All advertising materials mentioning features or use of this software
17 *    must display the following acknowledgement:
18 *        This product includes software developed by the NetBSD
19 *        Foundation, Inc. and its contributors.
20 * 4. Neither the name of The NetBSD Foundation nor the names of its
21 *    contributors may be used to endorse or promote products derived
22 *    from this software without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
25 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
26 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
27 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
28 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
29 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
30 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
31 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
32 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
33 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
34 * POSSIBILITY OF SUCH DAMAGE.
35 */
36
37#ifndef _h_chartype_f
38#define _h_chartype_f
39
40
41
42#ifdef WIDECHAR
43
44/* Ideally we should also test the value of the define to see if it
45 * supports non-BMP code points without requiring UTF-16, but nothing
46 * seems to actually advertise this properly, despite Unicode 3.1 having
47 * been around since 2001... */
48#if !defined(__NetBSD__) && !defined(__OpenBSD__)
49#ifndef __STDC_ISO_10646__
50/* In many places it is assumed that the first 127 code points are ASCII
51 * compatible, so ensure wchar_t indeed does ISO 10646 and not some other
52 * funky encoding that could break us in weird and wonderful ways. */
53	#error wchar_t must store ISO 10646 characters
54#endif
55#endif
56
57/* Oh for a <uchar.h> with char32_t and __STDC_UTF_32__ in it...
58 * ref: ISO/IEC DTR 19769
59 */
60#if WCHAR_MAX < INT32_MAX
61#warning Build environment does not support non-BMP characters
62#endif
63
64#define ct_mbrtowc           mbrtowc
65#define ct_wctob             wctob
66#define ct_wctomb            wctomb
67#define ct_wctomb_reset      wctomb(0,0)
68#define ct_wcstombs          wcstombs
69#define ct_mbstowcs          mbstowcs
70
71#define Char			wchar_t
72#define FUN(prefix,rest)	prefix ## _w ## rest
73#define FUNW(type)		type ## _w
74#define TYPE(type)		type ## W
75#define FSTR			"%ls"
76#define STR(x) 			L ## x
77#define UC(c)			c
78#define Isalpha(x)  iswalpha(x)
79#define Isalnum(x)  iswalnum(x)
80#define Isgraph(x)  iswgraph(x)
81#define Isspace(x)  iswspace(x)
82#define Isdigit(x)  iswdigit(x)
83#define Iscntrl(x)  iswcntrl(x)
84#define Isprint(x)  iswprint(x)
85
86#define Isupper(x)  iswupper(x)
87#define Islower(x)  iswlower(x)
88#define Toupper(x)  towupper(x)
89#define Tolower(x)  towlower(x)
90
91#define IsASCII(x)  (x < 0x100)
92
93#define Strlen(x)       wcslen(x)
94#define Strchr(s,c)     wcschr(s,c)
95#define Strrchr(s,c)    wcsrchr(s,c)
96#define Strstr(s,v)     wcsstr(s,v)
97#define Strdup(x)       wcsdup(x)
98/* #define Strcpy(d,s)     wcscpy(d,s) */
99#define Strncpy(d,s,n)  wcsncpy(d,s,n)
100#define Strncat(d,s,n)  wcsncat(d,s,n)
101
102#define Strcmp(s,v)     wcscmp(s,v)
103#define Strncmp(s,v,n)  wcsncmp(s,v,n)
104#define Strcspn(s,r)    wcscspn(s,r)
105
106#define Strtol(p,e,b)   wcstol(p,e,b)
107
108#define Width(c)	(wcwidth(c) == -1 ? 0 : wcwidth(c))
109
110#else /* NARROW */
111
112size_t 	ct_mbrtowc(char *, const char *, size_t, void *);
113#define ct_wctob(w)          ((int)(w))
114#define ct_wctomb            error
115#define ct_wctomb_reset
116#define ct_wcstombs(a, b, c)    (strncpy(a, b, c), strlen(a))
117#define ct_mbstowcs(a, b, c)    (strncpy(a, b, c), strlen(a))
118
119#define Char			char
120#define FUN(prefix,rest)	prefix ## _ ## rest
121#define FUNW(type)		type
122#define TYPE(type)		type
123#define FSTR			"%s"
124#define STR(x) 			x
125#define UC(c)			(unsigned char)(c)
126
127#define Isalpha(x)  isalpha((unsigned char)x)
128#define Isalnum(x)  isalnum((unsigned char)x)
129#define Isgraph(x)  isgraph((unsigned char)x)
130#define Isspace(x)  isspace((unsigned char)x)
131#define Isdigit(x)  isdigit((unsigned char)x)
132#define Iscntrl(x)  iscntrl((unsigned char)x)
133#define Isprint(x)  isprint((unsigned char)x)
134
135#define Isupper(x)  isupper((unsigned char)x)
136#define Islower(x)  islower((unsigned char)x)
137#define Toupper(x)  toupper((unsigned char)x)
138#define Tolower(x)  tolower((unsigned char)x)
139
140#define IsASCII(x)  isascii((unsigned char)x)
141
142#define Strlen(x)       strlen(x)
143#define Strchr(s,c)     strchr(s,c)
144#define Strrchr(s,c)    strrchr(s,c)
145#define Strstr(s,v)     strstr(s,v)
146#define Strdup(x)       strdup(x)
147/* #define Strcpy(d,s)     strcpy(d,s) */
148#define Strncpy(d,s,n)  strncpy(d,s,n)
149#define Strncat(d,s,n)  strncat(d,s,n)
150
151#define Strcmp(s,v)     strcmp(s,v)
152#define Strncmp(s,v,n)  strncmp(s,v,n)
153#define Strcspn(s,r)    strcspn(s,r)
154
155#define Strtol(p,e,b)   strtol(p,e,b)
156
157#define Width(c)	1
158
159#endif
160
161
162#ifdef WIDECHAR
163/*
164 * Conversion buffer
165 */
166typedef struct ct_buffer_t {
167        char    *cbuff;
168        size_t  csize;
169        Char *wbuff;
170        size_t  wsize;
171} ct_buffer_t;
172
173#define ct_encode_string __ct_encode_string
174/* Encode a wide-character string and return the UTF-8 encoded result. */
175public char *ct_encode_string(const Char *, ct_buffer_t *);
176
177#define ct_decode_string __ct_decode_string
178/* Decode a (multi)?byte string and return the wide-character string result. */
179public Char *ct_decode_string(const char *, ct_buffer_t *);
180
181/* Decode a (multi)?byte argv string array.
182 * The pointer returned must be free()d when done. */
183protected Char **ct_decode_argv(int, const char *[],  ct_buffer_t *);
184
185/* Resizes the conversion buffer(s) if needed. */
186protected void ct_conv_buff_resize(ct_buffer_t *, size_t, size_t);
187protected ssize_t ct_encode_char(char *, size_t, Char);
188protected size_t ct_enc_width(Char);
189
190#define ct_free_argv(s)	free(s)
191
192#else
193#define	ct_encode_string(s, b)	(s)
194#define ct_decode_string(s, b)	(s)
195#define ct_decode_argv(l, s, b)	(s)
196#define ct_conv_buff_resize(b, os, ns)
197#define ct_encode_char(d, l, s)	(*d = s, 1)
198#define ct_free_argv(s)
199#endif
200
201#ifndef NARROWCHAR
202/* Encode a characted into the destination buffer, provided there is sufficent
203 * buffer space available. Returns the number of bytes used up (zero if the
204 * character cannot be encoded, -1 if there was not enough space available). */
205
206/* The maximum buffer size to hold the most unwieldly visual representation,
207 * in this case \U+nnnnn. */
208#define VISUAL_WIDTH_MAX 8
209
210/* The terminal is thought of in terms of X columns by Y lines. In the cases
211 * where a wide character takes up more than one column, the adjacent
212 * occupied column entries will contain this faux character. */
213#define MB_FILL_CHAR ((Char)-1)
214
215/* Visual width of character c, taking into account ^? , \0177 and \U+nnnnn
216 * style visual expansions. */
217protected int ct_visual_width(Char);
218
219/* Turn the given character into the appropriate visual format, matching
220 * the width given by ct_visual_width(). Returns the number of characters used
221 * up, or -1 if insufficient space. Buffer length is in count of Char's. */
222protected ssize_t ct_visual_char(Char *, size_t, Char);
223
224/* Convert the given string into visual format, using the ct_visual_char()
225 * function. Uses a static buffer, so not threadsafe. */
226protected const Char *ct_visual_string(const Char *);
227
228
229/* printable character, use ct_visual_width() to find out display width */
230#define CHTYPE_PRINT        ( 0)
231/* control character found inside the ASCII portion of the charset */
232#define CHTYPE_ASCIICTL     (-1)
233/* a \t */
234#define CHTYPE_TAB          (-2)
235/* a \n */
236#define CHTYPE_NL           (-3)
237/* non-printable character */
238#define CHTYPE_NONPRINT     (-4)
239/* classification of character c, as one of the above defines */
240protected int ct_chr_class(Char c);
241#endif
242
243
244#endif /* _chartype_f */
245