Project: Git
Code Location: git://github.com/git/git.gitmaster
Browse
/
Outline
Download File
utf8.c
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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
#include "git-compat-util.h"
#include "strbuf.h"
#include "utf8.h"

/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */

struct interval {
	ucs_char_t first;
	ucs_char_t last;
};

size_t display_mode_esc_sequence_len(const char *s)
{
	const char *p = s;
	if (*p++ != '\033')
		return 0;
	if (*p++ != '[')
		return 0;
	while (isdigit(*p) || *p == ';')
		p++;
	if (*p++ != 'm')
		return 0;
	return p - s;
}

/* auxiliary function for binary search in interval table */
static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
{
	int min = 0;
	int mid;

	if (ucs < table[0].first || ucs > table[max].last)
		return 0;
	while (max >= min) {
		mid = (min + max) / 2;
		if (ucs > table[mid].last)
			min = mid + 1;
		else if (ucs < table[mid].first)
			max = mid - 1;
		else
			return 1;
	}

	return 0;
}

/* The following two functions define the column width of an ISO 10646
 * character as follows:
 *
 *    - The null character (U+0000) has a column width of 0.
 *
 *    - Other C0/C1 control characters and DEL will lead to a return
 *      value of -1.
 *
 *    - Non-spacing and enclosing combining characters (general
 *      category code Mn or Me in the Unicode database) have a
 *      column width of 0.
 *
 *    - SOFT HYPHEN (U+00AD) has a column width of 1.
 *
 *    - Other format characters (general category code Cf in the Unicode
 *      database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
 *
 *    - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
 *      have a column width of 0.
 *
 *    - Spacing characters in the East Asian Wide (W) or East Asian
 *      Full-width (F) category as defined in Unicode Technical
 *      Report #11 have a column width of 2.
 *
 *    - All remaining characters (including all printable
 *      ISO 8859-1 and WGL4 characters, Unicode control characters,
 *      etc.) have a column width of 1.
 *
 * This implementation assumes that ucs_char_t characters are encoded
 * in ISO 10646.
 */

static int git_wcwidth(ucs_char_t ch)
{
	/*
	 * Sorted list of non-overlapping intervals of non-spacing characters,
	 * generated by
	 *   "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c".
	 */
	static const struct interval combining[] = {
		{ 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD },
		{ 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
		{ 0x05C7, 0x05C7 }, { 0x0600, 0x0604 }, { 0x0610, 0x061A },
		{ 0x064B, 0x065F }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
		{ 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
		{ 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
		{ 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
		{ 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 },
		{ 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 },
		{ 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 },
		{ 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 },
		{ 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 },
		{ 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 },
		{ 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 },
		{ 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 },
		{ 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 },
		{ 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
		{ 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
		{ 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 },
		{ 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
		{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
		{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
		{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
		{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
		{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
		{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
		{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
		{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
		{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x1712, 0x1714 },
		{ 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 },
		{ 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
		{ 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D },
		{ 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 },
		{ 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x200B, 0x200F },
		{ 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F },
		{ 0x20D0, 0x20EA }, { 0x302A, 0x302F }, { 0x3099, 0x309A },
		{ 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 },
		{ 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 },
		{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B },
		{ 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 },
		{ 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF }
	};

	/* test for 8-bit control characters */
	if (ch == 0)
		return 0;
	if (ch < 32 || (ch >= 0x7f && ch < 0xa0))
		return -1;

	/* binary search in table of non-spacing characters */
	if (bisearch(ch, combining, sizeof(combining)
				/ sizeof(struct interval) - 1))
		return 0;

	/*
	 * If we arrive here, ch is neither a combining nor a C0/C1
	 * control character.
	 */

	return 1 +
		(ch >= 0x1100 &&
                    /* Hangul Jamo init. consonants */
		 (ch <= 0x115f ||
		  ch == 0x2329 || ch == 0x232a ||
                  /* CJK ... Yi */
		  (ch >= 0x2e80 && ch <= 0xa4cf &&
		   ch != 0x303f) ||
		  /* Hangul Syllables */
		  (ch >= 0xac00 && ch <= 0xd7a3) ||
		  /* CJK Compatibility Ideographs */
		  (ch >= 0xf900 && ch <= 0xfaff) ||
		  /* CJK Compatibility Forms */
		  (ch >= 0xfe30 && ch <= 0xfe6f) ||
		  /* Fullwidth Forms */
		  (ch >= 0xff00 && ch <= 0xff60) ||
		  (ch >= 0xffe0 && ch <= 0xffe6) ||
		  (ch >= 0x20000 && ch <= 0x2fffd) ||
		  (ch >= 0x30000 && ch <= 0x3fffd)));
}

/*
 * Pick one ucs character starting from the location *start points at,
 * and return it, while updating the *start pointer to point at the
 * end of that character.  When remainder_p is not NULL, the location
 * holds the number of bytes remaining in the string that we are allowed
 * to pick from.  Otherwise we are allowed to pick up to the NUL that
 * would eventually appear in the string.  *remainder_p is also reduced
 * by the number of bytes we have consumed.
 *
 * If the string was not a valid UTF-8, *start pointer is set to NULL
 * and the return value is undefined.
 */
static ucs_char_t pick_one_utf8_char(const char **start, size_t *remainder_p)
{
	unsigned char *s = (unsigned char *)*start;
	ucs_char_t ch;
	size_t remainder, incr;

	/*
	 * A caller that assumes NUL terminated text can choose
	 * not to bother with the remainder length.  We will
	 * stop at the first NUL.
	 */
	remainder = (remainder_p ? *remainder_p : 999);

	if (remainder < 1) {
		goto invalid;
	} else if (*s < 0x80) {
		/* 0xxxxxxx */
		ch = *s;
		incr = 1;
	} else if ((s[0] & 0xe0) == 0xc0) {
		/* 110XXXXx 10xxxxxx */
		if (remainder < 2 ||
		    (s[1] & 0xc0) != 0x80 ||
		    (s[0] & 0xfe) == 0xc0)
			goto invalid;
		ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
		incr = 2;
	} else if ((s[0] & 0xf0) == 0xe0) {
		/* 1110XXXX 10Xxxxxx 10xxxxxx */
		if (remainder < 3 ||
		    (s[1] & 0xc0) != 0x80 ||
		    (s[2] & 0xc0) != 0x80 ||
		    /* overlong? */
		    (s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) ||
		    /* surrogate? */
		    (s[0] == 0xed && (s[1] & 0xe0) == 0xa0) ||
		    /* U+FFFE or U+FFFF? */
		    (s[0] == 0xef && s[1] == 0xbf &&
		     (s[2] & 0xfe) == 0xbe))
			goto invalid;
		ch = ((s[0] & 0x0f) << 12) |
			((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
		incr = 3;
	} else if ((s[0] & 0xf8) == 0xf0) {
		/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
		if (remainder < 4 ||
		    (s[1] & 0xc0) != 0x80 ||
		    (s[2] & 0xc0) != 0x80 ||
		    (s[3] & 0xc0) != 0x80 ||
		    /* overlong? */
		    (s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||
		    /* > U+10FFFF? */
		    (s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4)
			goto invalid;
		ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) |
			((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
		incr = 4;
	} else {
invalid:
		*start = NULL;
		return 0;
	}

	*start += incr;
	if (remainder_p)
		*remainder_p = remainder - incr;
	return ch;
}

/*
 * This function returns the number of columns occupied by the character
 * pointed to by the variable start. The pointer is updated to point at
 * the next character. When remainder_p is not NULL, it points at the
 * location that stores the number of remaining bytes we can use to pick
 * a character (see pick_one_utf8_char() above).
 */
int utf8_width(const char **start, size_t *remainder_p)
{
	ucs_char_t ch = pick_one_utf8_char(start, remainder_p);
	if (!*start)
		return 0;
	return git_wcwidth(ch);
}

/*
 * Returns the total number of columns required by a null-terminated
 * string, assuming that the string is utf8.  Returns strlen() instead
 * if the string does not look like a valid utf8 string.
 */
int utf8_strnwidth(const char *string, int len, int skip_ansi)
{
	int width = 0;
	const char *orig = string;

	if (len == -1)
		len = strlen(string);
	while (string && string < orig + len) {
		int skip;
		while (skip_ansi &&
		       (skip = display_mode_esc_sequence_len(string)) != 0)
			string += skip;
		width += utf8_width(&string, NULL);
	}
	return string ? width : len;
}

int utf8_strwidth(const char *string)
{
	return utf8_strnwidth(string, -1, 0);
}

int is_utf8(const char *text)
{
	while (*text) {
		if (*text == '\n' || *text == '\t' || *text == '\r') {
			text++;
			continue;
		}
		utf8_width(&text, NULL);
		if (!text)
			return 0;
	}
	return 1;
}

static void strbuf_addchars(struct strbuf *sb, int c, size_t n)
{
	strbuf_grow(sb, n);
	memset(sb->buf + sb->len, c, n);
	strbuf_setlen(sb, sb->len + n);
}

static void strbuf_add_indented_text(struct strbuf *buf, const char *text,
				     int indent, int indent2)
{
	if (indent < 0)
		indent = 0;
	while (*text) {
		const char *eol = strchrnul(text, '\n');
		if (*eol == '\n')
			eol++;
		strbuf_addchars(buf, ' ', indent);
		strbuf_add(buf, text, eol - text);
		text = eol;
		indent = indent2;
	}
}

/*
 * Wrap the text, if necessary. The variable indent is the indent for the
 * first line, indent2 is the indent for all other lines.
 * If indent is negative, assume that already -indent columns have been
 * consumed (and no extra indent is necessary for the first line).
 */
void strbuf_add_wrapped_text(struct strbuf *buf,
		const char *text, int indent1, int indent2, int width)
{
	int indent, w, assume_utf8 = 1;
	const char *bol, *space, *start = text;
	size_t orig_len = buf->len;

	if (width <= 0) {
		strbuf_add_indented_text(buf, text, indent1, indent2);
		return;
	}

retry:
	bol = text;
	w = indent = indent1;
	space = NULL;
	if (indent < 0) {
		w = -indent;
		space = text;
	}

	for (;;) {
		char c;
		size_t skip;

		while ((skip = display_mode_esc_sequence_len(text)))
			text += skip;

		c = *text;
		if (!c || isspace(c)) {
			if (w <= width || !space) {
				const char *start = bol;
				if (!c && text == start)
					return;
				if (space)
					start = space;
				else
					strbuf_addchars(buf, ' ', indent);
				strbuf_add(buf, start, text - start);
				if (!c)
					return;
				space = text;
				if (c == '\t')
					w |= 0x07;
				else if (c == '\n') {
					space++;
					if (*space == '\n') {
						strbuf_addch(buf, '\n');
						goto new_line;
					}
					else if (!isalnum(*space))
						goto new_line;
					else
						strbuf_addch(buf, ' ');
				}
				w++;
				text++;
			}
			else {
new_line:
				strbuf_addch(buf, '\n');
				text = bol = space + isspace(*space);
				space = NULL;
				w = indent = indent2;
			}
			continue;
		}
		if (assume_utf8) {
			w += utf8_width(&text, NULL);
			if (!text) {
				assume_utf8 = 0;
				text = start;
				strbuf_setlen(buf, orig_len);
				goto retry;
			}
		} else {
			w++;
			text++;
		}
	}
}

void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
			     int indent, int indent2, int width)
{
	char *tmp = xstrndup(data, len);
	strbuf_add_wrapped_text(buf, tmp, indent, indent2, width);
	free(tmp);
}

void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
			 const char *subst)
{
	struct strbuf sb_dst = STRBUF_INIT;
	char *src = sb_src->buf;
	char *end = src + sb_src->len;
	char *dst;
	int w = 0, subst_len = 0;

	if (subst)
		subst_len = strlen(subst);
	strbuf_grow(&sb_dst, sb_src->len + subst_len);
	dst = sb_dst.buf;

	while (src < end) {
		char *old;
		size_t n;

		while ((n = display_mode_esc_sequence_len(src))) {
			memcpy(dst, src, n);
			src += n;
			dst += n;
		}

		old = src;
		n = utf8_width((const char**)&src, NULL);
		if (!src) 	/* broken utf-8, do nothing */
			return;
		if (n && w >= pos && w < pos + width) {
			if (subst) {
				memcpy(dst, subst, subst_len);
				dst += subst_len;
				subst = NULL;
			}
			w += n;
			continue;
		}
		memcpy(dst, old, src - old);
		dst += src - old;
		w += n;
	}
	strbuf_setlen(&sb_dst, dst - sb_dst.buf);
	strbuf_swap(sb_src, &sb_dst);
	strbuf_release(&sb_dst);
}

int is_encoding_utf8(const char *name)
{
	if (!name)
		return 1;
	if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8"))
		return 1;
	return 0;
}

int same_encoding(const char *src, const char *dst)
{
	if (is_encoding_utf8(src) && is_encoding_utf8(dst))
		return 1;
	return !strcasecmp(src, dst);
}

/*
 * Wrapper for fprintf and returns the total number of columns required
 * for the printed string, assuming that the string is utf8.
 */
int utf8_fprintf(FILE *stream, const char *format, ...)
{
	struct strbuf buf = STRBUF_INIT;
	va_list arg;
	int columns;

	va_start(arg, format);
	strbuf_vaddf(&buf, format, arg);
	va_end(arg);

	columns = fputs(buf.buf, stream);
	if (0 <= columns) /* keep the error from the I/O */
		columns = utf8_strwidth(buf.buf);
	strbuf_release(&buf);
	return columns;
}

/*
 * Given a buffer and its encoding, return it re-encoded
 * with iconv.  If the conversion fails, returns NULL.
 */
#ifndef NO_ICONV
#if defined(OLD_ICONV) || (defined(__sun__) && !defined(_XPG6))
	typedef const char * iconv_ibp;
#else
	typedef char * iconv_ibp;
#endif
char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p)
{
	size_t outsz, outalloc;
	char *out, *outpos;
	iconv_ibp cp;

	outsz = insz;
	outalloc = outsz + 1; /* for terminating NUL */
	out = xmalloc(outalloc);
	outpos = out;
	cp = (iconv_ibp)in;

	while (1) {
		size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);

		if (cnt == (size_t) -1) {
			size_t sofar;
			if (errno != E2BIG) {
				free(out);
				return NULL;
			}
			/* insz has remaining number of bytes.
			 * since we started outsz the same as insz,
			 * it is likely that insz is not enough for
			 * converting the rest.
			 */
			sofar = outpos - out;
			outalloc = sofar + insz * 2 + 32;
			out = xrealloc(out, outalloc);
			outpos = out + sofar;
			outsz = outalloc - sofar - 1;
		}
		else {
			*outpos = '\0';
			if (outsz_p)
				*outsz_p = outpos - out;
			break;
		}
	}
	return out;
}

char *reencode_string_len(const char *in, int insz,
			  const char *out_encoding, const char *in_encoding,
			  int *outsz)
{
	iconv_t conv;
	char *out;

	if (!in_encoding)
		return NULL;

	conv = iconv_open(out_encoding, in_encoding);
	if (conv == (iconv_t) -1) {
		/*
		 * Some platforms do not have the variously spelled variants of
		 * UTF-8, so let's fall back to trying the most official
		 * spelling. We do so only as a fallback in case the platform
		 * does understand the user's spelling, but not our official
		 * one.
		 */
		if (is_encoding_utf8(in_encoding))
			in_encoding = "UTF-8";
		if (is_encoding_utf8(out_encoding))
			out_encoding = "UTF-8";
		conv = iconv_open(out_encoding, in_encoding);
		if (conv == (iconv_t) -1)
			return NULL;
	}

	out = reencode_string_iconv(in, insz, conv, outsz);
	iconv_close(conv);
	return out;
}
#endif

/*
 * Returns first character length in bytes for multi-byte `text` according to
 * `encoding`.
 *
 * - The `text` pointer is updated to point at the next character.
 * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
 *   we can consume from text, and on exit `*remainder_p` is reduced by returned
 *   character length. Otherwise `text` is treated as limited by NUL.
 */
int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
{
	int chrlen;
	const char *p = *text;
	size_t r = (remainder_p ? *remainder_p : SIZE_MAX);

	if (r < 1)
		return 0;

	if (is_encoding_utf8(encoding)) {
		pick_one_utf8_char(&p, &r);

		chrlen = p ? (p - *text)
			   : 1 /* not valid UTF-8 -> raw byte sequence */;
	}
	else {
		/*
		 * TODO use iconv to decode one char and obtain its chrlen
		 * for now, let's treat encodings != UTF-8 as one-byte
		 */
		chrlen = 1;
	}

	*text += chrlen;
	if (remainder_p)
		*remainder_p -= chrlen;

	return chrlen;
}