23 	while (i >= 0 && utf8agetab[i] != 0) {  in utf8version_is_supported()
28 	return 0;  in utf8version_is_supported()
45  * 0x00000000 0x0000007F: 0xxxxxxx
46  * 0x00000000 0x000007FF: 110xxxxx 10xxxxxx
47  * 0x00000000 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
48  * 0x00000000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
49  * 0x00000000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
50  * 0x00000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
57  * 0x00000000 0x0000007F: 0xxxxxxx
58  * 0x00000080 0x000007FF: 110xxxxx 10xxxxxx
59  * 0x00000800 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
60  * 0x00010000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
61  * 0x00200000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
62  * 0x04000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
64  * Actual unicode characters are limited to the range 0x0 - 0x10FFFF,
68  *          0 -     0x7F: 0                   - 0x7F
69  *       0x80 -    0x7FF: 0xC2 0x80           - 0xDF 0xBF
70  *      0x800 -   0xFFFF: 0xE0 0xA0 0x80      - 0xEF 0xBF 0xBF
71  *    0x10000 - 0x10FFFF: 0xF0 0x90 0x80 0x80 - 0xF4 0x8F 0xBF 0xBF
73  * Within those ranges the surrogates 0xD800 - 0xDFFF are not allowed.
95 	return 1 + (c >= 0xC0) + (c >= 0xE0) + (c >= 0xF0);  in utf8clen()
106 	uc = *str++ & 0x0F;  in utf8decode3()
108 	uc |= *str++ & 0x3F;  in utf8decode3()
110 	uc |= *str++ & 0x3F;  in utf8decode3()
121 	str[2] = (val & 0x3F) | 0x80;  in utf8encode3()
123 	str[1] = (val & 0x3F) | 0x80;  in utf8encode3()
125 	str[0] = val | 0xE0;  in utf8encode3()
141  * if offlen == 0 (non-branching node)
146  * if offlen != 0 (branching node)
155 #define BITNUM		0x07
156 #define NEXTBYTE	0x08
157 #define OFFLEN		0x30
159 #define RIGHTPATH	0x40
160 #define TRIENODE	0x80
161 #define RIGHTNODE	0x40
162 #define LEFTNODE	0x80
170  * leaf[0]: The unicode version, stored as a generation number that is
173  *          defined.  The CCC of a non-defined code point is 0.
177  *          a CCC of 0, or at the begin or end of a string.
179  *          between 0 and 254 inclusive, which leaves 255 available as
181  *          Code points with CCC 0 are known as stoppers.
189  *          These do affect normalization, as they all have CCC 0.
203 #define LEAF_GEN(LEAF)	((LEAF)[0])
207 #define MINCCC		(0)
209 #define STOPPER		(0)
218  * Hangul decomposition (algorithm from Section 3.12 of Unicode 6.3.0)
220  * AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
221  * D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
223  * SBase = 0xAC00
224  * LBase = 0x1100
225  * VBase = 0x1161
226  * TBase = 0x11A7
254  *   if (TIndex == 0) {
263 #define SB	(0xAC00)
264 #define LB	(0x1100)
265 #define VB	(0x1161)
266 #define TB	(0x11A7)
306 	h[0] = '\0';  in utf8hangul()
330 	if (len == 0)  in utf8nlookup()
338 			if (--len == 0)  in utf8nlookup()
380 	 * codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is  in utf8nlookup()
384 	if (LEAF_CCC(trie) == DECOMPOSE && LEAF_STR(trie)[0] == HANGUL)  in utf8nlookup()
404  * Return 0 if only non-assigned code points are used.
409 	int		age = 0;  in utf8agemax()
433  * Return 0 if non-assigned code points are used.
465 	int		age = 0;  in utf8nagemax()
518  * A string of Default_Ignorable_Code_Point has length 0.
523 	size_t		ret = 0;  in utf8len()
551 	size_t		ret = 0;  in utf8nlen()
581  * Returns -1 on error, 0 on success.
596 	u8c->slen = 0;  in utf8ncursor()
603 	if (len > 0 && (*s & 0xC0) == 0x80)  in utf8ncursor()
605 	return 0;  in utf8ncursor()
616  * Returns -1 on error, 0 on success.
637  * and the function returns 0 in that case.
659 		if (u8c->p && *u8c->s == '\0') {  in utf8byte()
665 		if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) {  in utf8byte()
668 				return 0;  in utf8byte()
672 		} else if ((*u8c->s & 0xC0) == 0x80) {  in utf8byte()
692 		/* Characters that are too new have CCC 0. */  in utf8byte()
699 			/* Empty decomposition implies CCC 0. */  in utf8byte()
700 			if (*u8c->s == '\0') {  in utf8byte()
764 			u8c->slen = 0;  in utf8byte()