File: utf8.c

package info (click to toggle)
tmate 2.4.0-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 2,560 kB
  • sloc: ansic: 38,233; awk: 339; makefile: 252; sh: 44; perl: 41
file content (401 lines) | stat: -rw-r--r-- 7,935 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
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
/* $OpenBSD$ */

/*
 * Copyright (c) 2008 Nicholas Marriott <nicholas.marriott@gmail.com>
 *
 * Permission to use, copy, modify, and 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 MIND, 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 <stdlib.h>
#include <string.h>
#include <wchar.h>

#include "tmux.h"

static int	utf8_width(wchar_t);

/* Set a single character. */
void
utf8_set(struct utf8_data *ud, u_char ch)
{
	u_int	i;

	*ud->data = ch;
	ud->have = 1;
	ud->size = 1;

	ud->width = 1;

	for (i = ud->size; i < sizeof ud->data; i++)
		ud->data[i] = '\0';
}

/* Copy UTF-8 character. */
void
utf8_copy(struct utf8_data *to, const struct utf8_data *from)
{
	u_int	i;

	memcpy(to, from, sizeof *to);

	for (i = to->size; i < sizeof to->data; i++)
		to->data[i] = '\0';
}

/*
 * Open UTF-8 sequence.
 *
 * 11000010-11011111 C2-DF start of 2-byte sequence
 * 11100000-11101111 E0-EF start of 3-byte sequence
 * 11110000-11110100 F0-F4 start of 4-byte sequence
 */
enum utf8_state
utf8_open(struct utf8_data *ud, u_char ch)
{
	memset(ud, 0, sizeof *ud);
	if (ch >= 0xc2 && ch <= 0xdf)
		ud->size = 2;
	else if (ch >= 0xe0 && ch <= 0xef)
		ud->size = 3;
	else if (ch >= 0xf0 && ch <= 0xf4)
		ud->size = 4;
	else
		return (UTF8_ERROR);
	utf8_append(ud, ch);
	return (UTF8_MORE);
}

/* Append character to UTF-8, closing if finished. */
enum utf8_state
utf8_append(struct utf8_data *ud, u_char ch)
{
	wchar_t	wc;
	int	width;

	if (ud->have >= ud->size)
		fatalx("UTF-8 character overflow");
	if (ud->size > sizeof ud->data)
		fatalx("UTF-8 character size too large");

	if (ud->have != 0 && (ch & 0xc0) != 0x80)
		ud->width = 0xff;

	ud->data[ud->have++] = ch;
	if (ud->have != ud->size)
		return (UTF8_MORE);

	if (ud->width == 0xff)
		return (UTF8_ERROR);

	if (utf8_combine(ud, &wc) != UTF8_DONE)
		return (UTF8_ERROR);
	if ((width = utf8_width(wc)) < 0)
		return (UTF8_ERROR);
	ud->width = width;

	return (UTF8_DONE);
}

/* Get width of Unicode character. */
static int
utf8_width(wchar_t wc)
{
	int	width;

	width = wcwidth(wc);
	if (width < 0 || width > 0xff)
		return (-1);
	return (width);
}

/* Combine UTF-8 into Unicode. */
enum utf8_state
utf8_combine(const struct utf8_data *ud, wchar_t *wc)
{
	switch (mbtowc(wc, ud->data, ud->size)) {
	case -1:
		mbtowc(NULL, NULL, MB_CUR_MAX);
		return (UTF8_ERROR);
	case 0:
		return (UTF8_ERROR);
	default:
		return (UTF8_DONE);
	}
}

/* Split Unicode into UTF-8. */
enum utf8_state
utf8_split(wchar_t wc, struct utf8_data *ud)
{
	char	s[MB_LEN_MAX];
	int	slen;

	slen = wctomb(s, wc);
	if (slen <= 0 || slen > (int)sizeof ud->data)
		return (UTF8_ERROR);

	memcpy(ud->data, s, slen);
	ud->size = slen;

	ud->width = utf8_width(wc);
	return (UTF8_DONE);
}

/*
 * Encode len characters from src into dst, which is guaranteed to have four
 * bytes available for each character from src (for \abc or UTF-8) plus space
 * for \0.
 */
int
utf8_strvis(char *dst, const char *src, size_t len, int flag)
{
	struct utf8_data	 ud;
	const char		*start, *end;
	enum utf8_state		 more;
	size_t			 i;

	start = dst;
	end = src + len;

	while (src < end) {
		if ((more = utf8_open(&ud, *src)) == UTF8_MORE) {
			while (++src < end && more == UTF8_MORE)
				more = utf8_append(&ud, *src);
			if (more == UTF8_DONE) {
				/* UTF-8 character finished. */
				for (i = 0; i < ud.size; i++)
					*dst++ = ud.data[i];
				continue;
			}
			/* Not a complete, valid UTF-8 character. */
			src -= ud.have;
		}
		if (src < end - 1)
			dst = vis(dst, src[0], flag, src[1]);
		else if (src < end)
			dst = vis(dst, src[0], flag, '\0');
		src++;
	}

	*dst = '\0';
	return (dst - start);
}

/*
 * Sanitize a string, changing any UTF-8 characters to '_'. Caller should free
 * the returned string. Anything not valid printable ASCII or UTF-8 is
 * stripped.
 */
char *
utf8_sanitize(const char *src)
{
	char			*dst;
	size_t			 n;
	enum utf8_state		 more;
	struct utf8_data	 ud;
	u_int			 i;

	dst = NULL;

	n = 0;
	while (*src != '\0') {
		dst = xreallocarray(dst, n + 1, sizeof *dst);
		if ((more = utf8_open(&ud, *src)) == UTF8_MORE) {
			while (*++src != '\0' && more == UTF8_MORE)
				more = utf8_append(&ud, *src);
			if (more == UTF8_DONE) {
				dst = xreallocarray(dst, n + ud.width,
				    sizeof *dst);
				for (i = 0; i < ud.width; i++)
					dst[n++] = '_';
				continue;
			}
			src -= ud.have;
		}
		if (*src > 0x1f && *src < 0x7f)
			dst[n++] = *src;
		else
			dst[n++] = '_';
		src++;
	}

	dst = xreallocarray(dst, n + 1, sizeof *dst);
	dst[n] = '\0';
	return (dst);
}

/*
 * Convert a string into a buffer of UTF-8 characters. Terminated by size == 0.
 * Caller frees.
 */
struct utf8_data *
utf8_fromcstr(const char *src)
{
	struct utf8_data	*dst;
	size_t			 n;
	enum utf8_state		 more;

	dst = NULL;

	n = 0;
	while (*src != '\0') {
		dst = xreallocarray(dst, n + 1, sizeof *dst);
		if ((more = utf8_open(&dst[n], *src)) == UTF8_MORE) {
			while (*++src != '\0' && more == UTF8_MORE)
				more = utf8_append(&dst[n], *src);
			if (more == UTF8_DONE) {
				n++;
				continue;
			}
			src -= dst[n].have;
		}
		utf8_set(&dst[n], *src);
		n++;
		src++;
	}

	dst = xreallocarray(dst, n + 1, sizeof *dst);
	dst[n].size = 0;
	return (dst);
}

/* Convert from a buffer of UTF-8 characters into a string. Caller frees. */
char *
utf8_tocstr(struct utf8_data *src)
{
	char	*dst;
	size_t	 n;

	dst = NULL;

	n = 0;
	for(; src->size != 0; src++) {
		dst = xreallocarray(dst, n + src->size, 1);
		memcpy(dst + n, src->data, src->size);
		n += src->size;
	}

	dst = xreallocarray(dst, n + 1, 1);
	dst[n] = '\0';
	return (dst);
}

/* Get width of UTF-8 string. */
u_int
utf8_cstrwidth(const char *s)
{
	struct utf8_data	tmp;
	u_int			width;
	enum utf8_state		more;

	width = 0;
	while (*s != '\0') {
		if ((more = utf8_open(&tmp, *s)) == UTF8_MORE) {
			while (*++s != '\0' && more == UTF8_MORE)
				more = utf8_append(&tmp, *s);
			if (more == UTF8_DONE) {
				width += tmp.width;
				continue;
			}
			s -= tmp.have;
		}
		if (*s > 0x1f && *s != 0x7f)
			width++;
		s++;
	}
	return (width);
}

/* Trim UTF-8 string to width. Caller frees. */
char *
utf8_trimcstr(const char *s, u_int width)
{
	struct utf8_data	*tmp, *next;
	char			*out;
	u_int			 at;

	tmp = utf8_fromcstr(s);

	at = 0;
	for (next = tmp; next->size != 0; next++) {
		if (at + next->width > width) {
			next->size = 0;
			break;
		}
		at += next->width;
	}

	out = utf8_tocstr(tmp);
	free(tmp);
	return (out);
}

/* Trim UTF-8 string to width. Caller frees. */
char *
utf8_rtrimcstr(const char *s, u_int width)
{
	struct utf8_data	*tmp, *next, *end;
	char			*out;
	u_int			 at;

	tmp = utf8_fromcstr(s);

	for (end = tmp; end->size != 0; end++)
		/* nothing */;
	if (end == tmp) {
		free(tmp);
		return (xstrdup(""));
	}
	next = end - 1;

	at = 0;
	for (;;)
	{
		if (at + next->width > width) {
			next++;
			break;
		}
		at += next->width;

		if (next == tmp)
			break;
		next--;
	}

	out = utf8_tocstr(next);
	free(tmp);
	return (out);
}

/* Pad UTF-8 string to width. Caller frees. */
char *
utf8_padcstr(const char *s, u_int width)
{
	size_t	 slen;
	char	*out;
	u_int	  n, i;

	n = utf8_cstrwidth(s);
	if (n >= width)
		return (xstrdup(s));

	slen = strlen(s);
	out = xmalloc(slen + 1 + (width - n));
	memcpy(out, s, slen);
	for (i = n; i < width; i++)
		out[slen++] = ' ';
	out[slen] = '\0';
	return (out);
}