Sync usage with man page.
[netbsd-mini2440.git] / lib / libedit / chartype.c
blobf48f988dcb5594d0f24e6a152ad7bfa0b8e20999
1 /* $NetBSD: chartype.c,v 1.1 2009/12/30 22:37:40 christos Exp $ */
3 /*-
4 * Copyright (c) 2009 The NetBSD Foundation, Inc.
5 * All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. All advertising materials mentioning features or use of this software
16 * must display the following acknowledgement:
17 * This product includes software developed by the NetBSD
18 * Foundation, Inc. and its contributors.
19 * 4. Neither the name of The NetBSD Foundation nor the names of its
20 * contributors may be used to endorse or promote products derived
21 * from this software without specific prior written permission.
23 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
24 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
25 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
26 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
27 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
28 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
29 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
30 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
31 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
32 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
33 * POSSIBILITY OF SUCH DAMAGE.
37 * chartype.c: character classification and meta information
39 #include "config.h"
40 #if !defined(lint) && !defined(SCCSID)
41 __RCSID("$NetBSD: chartype.c,v 1.1 2009/12/30 22:37:40 christos Exp $");
42 #endif /* not lint && not SCCSID */
43 #include "el.h"
44 #include <stdlib.h>
46 #define CT_BUFSIZ 1024
49 #ifdef WIDECHAR
50 protected void
51 ct_conv_buff_resize(ct_buffer_t *conv, size_t mincsize, size_t minwsize)
53 void *p;
54 if (mincsize > conv->csize) {
55 conv->csize = mincsize;
56 p = el_realloc(conv->cbuff, conv->csize);
57 if (p == NULL) {
58 conv->csize = 0;
59 el_free(conv->cbuff);
60 conv->cbuff = NULL;
61 } else
62 conv->cbuff = p;
65 if (minwsize > conv->wsize) {
66 conv->wsize = minwsize;
67 p = el_realloc(conv->wbuff, conv->wsize);
68 if (p == NULL) {
69 conv->wsize = 0;
70 el_free(conv->wbuff);
71 conv->wbuff = NULL;
72 } else
73 conv->wbuff = p;
78 public char *
79 ct_encode_string(const Char *s, ct_buffer_t *conv)
81 char *dst;
82 ssize_t used = 0;
84 if (!s)
85 return NULL;
86 if (!conv->cbuff)
87 ct_conv_buff_resize(conv, CT_BUFSIZ, 0);
88 if (!conv->cbuff)
89 return NULL;
91 dst = conv->cbuff;
92 while (*s) {
93 used = ct_encode_char(dst, (int)(conv->csize -
94 (dst - conv->cbuff)), *s);
95 if (used == -1) { /* failed to encode, need more buffer space */
96 used = dst - conv->cbuff;
97 ct_conv_buff_resize(conv, conv->csize + CT_BUFSIZ, 0);
98 if (!conv->cbuff)
99 return NULL;
100 dst = conv->cbuff + used;
101 /* don't increment s here - we want to retry it! */
103 else
104 ++s;
105 dst += used;
107 if (dst >= (conv->cbuff + conv->csize)) {
108 used = dst - conv->cbuff;
109 ct_conv_buff_resize(conv, conv->csize + 1, 0);
110 if (!conv->cbuff)
111 return NULL;
112 dst = conv->cbuff + used;
114 *dst = '\0';
115 return conv->cbuff;
118 public Char *
119 ct_decode_string(const char *s, ct_buffer_t *conv)
121 size_t len = 0;
123 if (!s)
124 return NULL;
125 if (!conv->wbuff)
126 ct_conv_buff_resize(conv, 0, CT_BUFSIZ);
127 if (!conv->wbuff)
128 return NULL;
130 len = ct_mbstowcs(0, s, 0);
131 if (len > conv->wsize)
132 ct_conv_buff_resize(conv, 0, len + 1);
133 if (!conv->wbuff)
134 return NULL;
135 ct_mbstowcs(conv->wbuff, s, conv->wsize);
136 return conv->wbuff;
140 protected Char **
141 ct_decode_argv(int argc, const char *argv[], ct_buffer_t *conv)
143 size_t bufspace;
144 int i;
145 Char *p;
146 Char **wargv;
147 ssize_t bytes;
149 /* Make sure we have enough space in the conversion buffer to store all
150 * the argv strings. */
151 for (i = 0, bufspace = 0; i < argc; ++i)
152 bufspace += argv[i] ? strlen(argv[i]) + 1 : 0;
153 ct_conv_buff_resize(conv, 0, bufspace);
154 if (!conv->wsize)
155 return NULL;
157 wargv = el_malloc(argc * sizeof(*wargv));
159 for (i = 0, p = conv->wbuff; i < argc; ++i) {
160 if (!argv[i]) { /* don't pass null pointers to mbstowcs */
161 wargv[i] = NULL;
162 bytes = -1;
163 } else {
164 wargv[i] = p;
165 bytes = mbstowcs(p, argv[i], bufspace);
167 if (bytes == -1) {
168 el_free(wargv);
169 return NULL;
170 } else
171 bytes++; /* include '\0' in the count */
172 bufspace -= bytes;
173 p += bytes;
176 return wargv;
180 private size_t
181 enc_width(Char c)
183 /* UTF-8 encoding specific values */
184 if (c < 0x80)
185 return 1;
186 else if (c < 0x0800)
187 return 2;
188 else if (c < 0x10000)
189 return 3;
190 else if (c < 0x110000)
191 return 4;
192 else
193 return 0; /* not a valid codepoint */
196 protected ssize_t
197 ct_encode_char(char *dst, size_t len, Char c)
199 ssize_t l = 0;
200 if (len < enc_width(c))
201 return -1;
202 l = ct_wctomb(dst, c);
204 if (l < 0) {
205 ct_wctomb_reset;
206 l = 0;
208 return l;
210 #endif
212 protected const Char *
213 ct_visual_string(const Char *s)
215 static Char *buff = NULL;
216 static size_t buffsize = 0;
217 void *p;
218 Char *dst;
219 ssize_t used = 0;
221 if (!s)
222 return NULL;
223 if (!buff) {
224 buffsize = CT_BUFSIZ;
225 buff = el_malloc(buffsize * sizeof(*buff));
227 dst = buff;
228 while (*s) {
229 used = ct_visual_char(dst, buffsize - (dst - buff), *s);
230 if (used == -1) { /* failed to encode, need more buffer space */
231 used = dst - buff;
232 buffsize += CT_BUFSIZ;
233 p = el_realloc(buff, buffsize * sizeof(*buff));
234 if (p == NULL)
235 goto out;
236 buff = p;
237 dst = buff + used;
238 /* don't increment s here - we want to retry it! */
240 else
241 ++s;
242 dst += used;
244 if (dst >= (buff + buffsize)) { /* sigh */
245 buffsize += 1;
246 p = el_realloc(buff, buffsize * sizeof(*buff));
247 if (p == NULL)
248 goto out;
249 buff = p;
250 dst = buff + buffsize - 1;
252 *dst = 0;
253 return buff;
254 out:
255 el_free(buff);
256 buffsize = 0;
257 return NULL;
262 protected int
263 ct_visual_width(Char c)
265 int t = ct_chr_class(c);
266 switch (t) {
267 case CHTYPE_ASCIICTL:
268 return 2; /* ^@ ^? etc. */
269 case CHTYPE_TAB:
270 return 1; /* Hmm, this really need to be handled outside! */
271 case CHTYPE_NL:
272 return 0; /* Should this be 1 instead? */
273 #ifdef WIDECHAR
274 case CHTYPE_PRINT:
275 return wcwidth(c);
276 case CHTYPE_NONPRINT:
277 if (c > 0xffff) /* prefer standard 4-byte display over 5-byte */
278 return 8; /* \U+12345 */
279 else
280 return 7; /* \U+1234 */
281 #else
282 case CHTYPE_PRINT:
283 return 1;
284 case CHTYPE_NONPRINT:
285 return 4; /* \123 */
286 #endif
287 default:
288 return 0; /* should not happen */
293 protected ssize_t
294 ct_visual_char(Char *dst, size_t len, Char c)
296 int t = ct_chr_class(c);
297 switch (t) {
298 case CHTYPE_ASCIICTL:
299 if (len < 2)
300 return -1; /* insufficient space */
301 *dst++ = '^';
302 if (c == '\177')
303 *dst = '?'; /* DEL -> ^? */
304 else
305 *dst = c | 0100; /* uncontrolify it */
306 return 2;
307 case CHTYPE_PRINT:
308 if (len < 1)
309 return -1; /* insufficient space */
310 *dst = c;
311 return 1;
312 case CHTYPE_NONPRINT:
313 /* we only use single-width glyphs for display,
314 * so this is right */
315 if ((ssize_t)len < ct_visual_width(c))
316 return -1; /* insufficient space */
317 #ifdef WIDECHAR
318 *dst++ = '\\';
319 *dst++ = 'U';
320 *dst++ = '+';
321 #define tohexdigit(v) "0123456789ABCDEF"[v]
322 if (c > 0xffff) /* prefer standard 4-byte display over 5-byte */
323 *dst++ = tohexdigit(((unsigned int) c >> 16) & 0xf);
324 *dst++ = tohexdigit(((unsigned int) c >> 12) & 0xf);
325 *dst++ = tohexdigit(((unsigned int) c >> 8) & 0xf);
326 *dst++ = tohexdigit(((unsigned int) c >> 4) & 0xf);
327 *dst = tohexdigit(((unsigned int) c ) & 0xf);
328 return (c > 0xffff) ? 8 : 7;
329 #else
330 *dst++ = '\\';
331 #define tooctaldigit(v) ((v) + '0')
332 *dst++ = tooctaldigit(((unsigned int) c >> 6) & 0x7);
333 *dst++ = tooctaldigit(((unsigned int) c >> 3) & 0x7);
334 *dst++ = tooctaldigit(((unsigned int) c ) & 0x7);
335 #endif
336 /*FALLTHROUGH*/
337 /* these two should be handled outside this function */
338 case CHTYPE_TAB:
339 case CHTYPE_NL:
340 default: /* we should never hit the default */
341 return 0;
348 protected int
349 ct_chr_class(Char c)
351 if (c == '\t')
352 return CHTYPE_TAB;
353 else if (c == '\n')
354 return CHTYPE_NL;
355 else if (IsASCII(c) && Iscntrl(c))
356 return CHTYPE_ASCIICTL;
357 else if (Isprint(c))
358 return CHTYPE_PRINT;
359 else
360 return CHTYPE_NONPRINT;