File: utf8.c

package info (click to toggle)
figlet 2.2.5-3
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, sid
  • size: 1,536 kB
  • ctags: 397
  • sloc: ansic: 3,611; sh: 174; makefile: 80; lisp: 37
file content (326 lines) | stat: -rw-r--r-- 7,584 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
#ifdef TLF_FONTS
/*
 * Copyright (c) 2007 Alexey Vatchenko <av@bsdua.org>
 *
 * Permission to use, copy, modify, and/or distribute this software for any
 * purpose with or without fee is hereby granted, provided that the above
 * copyright notice and this permission notice appear in all copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 */
#include <sys/types.h>

#include <wchar.h>
#include <arpa/inet.h>	/* for htonl() */

#include "utf8.h"

#define _NXT	0x80
#define _SEQ2	0xc0
#define _SEQ3	0xe0
#define _SEQ4	0xf0
#define _SEQ5	0xf8
#define _SEQ6	0xfc

#define _BOM	0xfeff

static int __wchar_forbitten(wchar_t sym);
static int __utf8_forbitten(u_char octet);

static int
__wchar_forbitten(wchar_t sym)
{

	/* Surrogate pairs */
	if (sym >= 0xd800 && sym <= 0xdfff)
		return (-1);

	return (0);
}

static int
__utf8_forbitten(u_char octet)
{

	switch (octet) {
	case 0xc0:
	case 0xc1:
	case 0xf5:
	case 0xff:
		return (-1);
	}

	return (0);
}

/*
 * DESCRIPTION
 *	This function translates UTF-8 string into UCS-4 string (all symbols
 *	will be in local machine byte order).
 *
 *	It takes the following arguments:
 *	in	- input UTF-8 string. It can be null-terminated.
 *	insize	- size of input string in bytes.
 *	out	- result buffer for UCS-4 string. If out is NULL,
 *		function returns size of result buffer.
 *	outsize - size of out buffer in wide characters.
 *
 * RETURN VALUES
 *	The function returns size of result buffer (in wide characters).
 *	Zero is returned in case of error.
 *
 * CAVEATS
 *	1. If UTF-8 string contains zero symbols, they will be translated
 *	   as regular symbols.
 *	2. If UTF8_IGNORE_ERROR or UTF8_SKIP_BOM flag is set, sizes may vary
 *	   when `out' is NULL and not NULL. It's because of special UTF-8
 *	   sequences which may result in forbitten (by RFC3629) UNICODE
 *	   characters.  So, the caller must check return value every time and
 *	   not prepare buffer in advance (\0 terminate) but after calling this
 *	   function.
 */
size_t
utf8_to_wchar(const char *in, size_t insize, wchar_t *out, size_t outsize,
    int flags)
{
	u_char *p, *lim;
	wchar_t *wlim, high;
	size_t n, total, i, n_bits;

	if (in == NULL || insize == 0 || (outsize == 0 && out != NULL))
		return (0);

	total = 0;
	p = (u_char *)in;
	lim = p + insize;
	wlim = out + outsize;

	for (; p < lim; p += n) {
		if (__utf8_forbitten(*p) != 0 &&
		    (flags & UTF8_IGNORE_ERROR) == 0)
			return (0);

		/*
		 * Get number of bytes for one wide character.
		 */
		n = 1;	/* default: 1 byte. Used when skipping bytes. */
		if ((*p & 0x80) == 0)
			high = (wchar_t)*p;
		else if ((*p & 0xe0) == _SEQ2) {
			n = 2;
			high = (wchar_t)(*p & 0x1f);
		} else if ((*p & 0xf0) == _SEQ3) {
			n = 3;
			high = (wchar_t)(*p & 0x0f);
		} else if ((*p & 0xf8) == _SEQ4) {
			n = 4;
			high = (wchar_t)(*p & 0x07);
		} else if ((*p & 0xfc) == _SEQ5) {
			n = 5;
			high = (wchar_t)(*p & 0x03);
		} else if ((*p & 0xfe) == _SEQ6) {
			n = 6;
			high = (wchar_t)(*p & 0x01);
		} else {
			if ((flags & UTF8_IGNORE_ERROR) == 0)
				return (0);
			continue;
		}

		/* does the sequence header tell us truth about length? */
		if (lim - p <= n - 1) {
			if ((flags & UTF8_IGNORE_ERROR) == 0)
				return (0);
			n = 1;
			continue;	/* skip */
		}

		/*
		 * Validate sequence.
		 * All symbols must have higher bits set to 10xxxxxx
		 */
		if (n > 1) {
			for (i = 1; i < n; i++) {
				if ((p[i] & 0xc0) != _NXT)
					break;
			}
			if (i != n) {
				if ((flags & UTF8_IGNORE_ERROR) == 0)
					return (0);
				n = 1;
				continue;	/* skip */
			}
		}

		total++;

		if (out == NULL)
			continue;

		if (out >= wlim)
			return (0);		/* no space left */

		*out = 0;
		n_bits = 0;
		for (i = 1; i < n; i++) {
			*out |= (wchar_t)(p[n - i] & 0x3f) << n_bits;
			n_bits += 6;		/* 6 low bits in every byte */
		}
		*out |= high << n_bits;

		if (*out == 0)			/* return at end of string */
			break;

		if (__wchar_forbitten(*out) != 0) {
			if ((flags & UTF8_IGNORE_ERROR) == 0)
				return (0);	/* forbitten character */
			else {
				total--;
				out--;
			}
		} else if (*out == _BOM && (flags & UTF8_SKIP_BOM) != 0) {
			total--;
			out--;
		}

		out++;
	}

	return (total);
}

/*
 * DESCRIPTION
 *	This function translates UCS-4 symbols (given in local machine
 *	byte order) into UTF-8 string.
 *
 *	It takes the following arguments:
 *	in	- input unicode string. It can be null-terminated.
 *	insize	- size of input string in wide characters.
 *	out	- result buffer for utf8 string. If out is NULL,
 *		function returns size of result buffer.
 *	outsize - size of result buffer.
 *
 * RETURN VALUES
 *	The function returns size of result buffer (in bytes). Zero is returned
 *	in case of error.
 *
 * CAVEATS
 *	If UCS-4 string contains zero symbols, they will be translated
 *	as regular symbols.
 */
size_t
wchar_to_utf8(const wchar_t *in, size_t insize, char *out, size_t outsize,
    int flags)
{
	wchar_t *w, *wlim, ch;
	u_char *p, *lim, *oc;
	size_t total, n;

	if (in == NULL || insize == 0 || (outsize == 0 && out != NULL))
		return (0);

	w = (wchar_t *)in;
	wlim = w + insize;
	p = (u_char *)out;
	lim = p + outsize;
	total = 0;
	for (; w < wlim; w++) {
		if (__wchar_forbitten(*w) != 0) {
			if ((flags & UTF8_IGNORE_ERROR) == 0)
				return (0);
			else
				continue;
		}

		if (*w == _BOM && (flags & UTF8_SKIP_BOM) != 0)
			continue;

		if (*w < 0) {
			if ((flags & UTF8_IGNORE_ERROR) == 0)
				return (0);
			continue;
		} else if (*w <= 0x0000007f)
			n = 1;
		else if (*w <= 0x000007ff)
			n = 2;
		else if (*w <= 0x0000ffff)
			n = 3;
		else if (*w <= 0x001fffff)
			n = 4;
		else if (*w <= 0x03ffffff)
			n = 5;
		else /* if (*w <= 0x7fffffff) */
			n = 6;

		total += n;

		if (out == NULL)
			continue;

		if (lim - p <= n - 1)
			return (0);		/* no space left */

		/* make it work under different endians */
		ch = htonl(*w);
		oc = (u_char *)&ch;
		switch (n) {
		case 1:
			*p = oc[3];
			break;

		case 2:
			p[1] = _NXT | (oc[3] & 0x3f);
			p[0] = _SEQ2 | (oc[3] >> 6) | ((oc[2] & 0x07) << 2);
			break;

		case 3:
			p[2] = _NXT | (oc[3] & 0x3f);
			p[1] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
			p[0] = _SEQ3 | ((oc[2] & 0xf0) >> 4);
			break;

		case 4:
			p[3] = _NXT | (oc[3] & 0x3f);
			p[2] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
			p[1] = _NXT | ((oc[2] & 0xf0) >> 4) |
			    ((oc[1] & 0x03) << 4);
			p[0] = _SEQ4 | ((oc[1] & 0x1f) >> 2);
			break;

		case 5:
			p[4] = _NXT | (oc[3] & 0x3f);
			p[3] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
			p[2] = _NXT | ((oc[2] & 0xf0) >> 4) |
			    ((oc[1] & 0x03) << 4);
			p[1] = _NXT | (oc[1] >> 2);
			p[0] = _SEQ5 | (oc[0] & 0x03);
			break;

		case 6:
			p[5] = _NXT | (oc[3] & 0x3f);
			p[4] = _NXT | (oc[3] >> 6) | ((oc[2] & 0x0f) << 2);
			p[3] = _NXT | (oc[2] >> 4) | ((oc[1] & 0x03) << 4);
			p[2] = _NXT | (oc[1] >> 2);
			p[1] = _NXT | (oc[0] & 0x3f);
			p[0] = _SEQ6 | ((oc[0] & 0x40) >> 6);
			break;
		}

		/*
		 * NOTE: do not check here for forbitten UTF-8 characters.
		 * They cannot appear here because we do proper convertion.
		 */

		p += n;
	}

	return (total);
}
#endif /* TLF_FONTS */