13 	while (i >= 0 && um->tables->utf8agetab[i] != 0) {  in utf8version_is_supported()
18 	return 0;  in utf8version_is_supported()
28  * 0x00000000 0x0000007F: 0xxxxxxx
29  * 0x00000000 0x000007FF: 110xxxxx 10xxxxxx
30  * 0x00000000 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
31  * 0x00000000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
32  * 0x00000000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
33  * 0x00000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
40  * 0x00000000 0x0000007F: 0xxxxxxx
41  * 0x00000080 0x000007FF: 110xxxxx 10xxxxxx
42  * 0x00000800 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
43  * 0x00010000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
44  * 0x00200000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
45  * 0x04000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
47  * Actual unicode characters are limited to the range 0x0 - 0x10FFFF,
51  *          0 -     0x7F: 0                   - 0x7F
52  *       0x80 -    0x7FF: 0xC2 0x80           - 0xDF 0xBF
53  *      0x800 -   0xFFFF: 0xE0 0xA0 0x80      - 0xEF 0xBF 0xBF
54  *    0x10000 - 0x10FFFF: 0xF0 0x90 0x80 0x80 - 0xF4 0x8F 0xBF 0xBF
56  * Within those ranges the surrogates 0xD800 - 0xDFFF are not allowed.
78 	return 1 + (c >= 0xC0) + (c >= 0xE0) + (c >= 0xF0);  in utf8clen()
89 	uc = *str++ & 0x0F;  in utf8decode3()
91 	uc |= *str++ & 0x3F;  in utf8decode3()
93 	uc |= *str++ & 0x3F;  in utf8decode3()
104 	str[2] = (val & 0x3F) | 0x80;  in utf8encode3()
106 	str[1] = (val & 0x3F) | 0x80;  in utf8encode3()
108 	str[0] = val | 0xE0;  in utf8encode3()
124  * if offlen == 0 (non-branching node)
129  * if offlen != 0 (branching node)
138 #define BITNUM		0x07
139 #define NEXTBYTE	0x08
140 #define OFFLEN		0x30
142 #define RIGHTPATH	0x40
143 #define TRIENODE	0x80
144 #define RIGHTNODE	0x40
145 #define LEFTNODE	0x80
153  * leaf[0]: The unicode version, stored as a generation number that is
156  *          defined.  The CCC of a non-defined code point is 0.
160  *          a CCC of 0, or at the begin or end of a string.
162  *          between 0 and 254 inclusive, which leaves 255 available as
164  *          Code points with CCC 0 are known as stoppers.
172  *          These do affect normalization, as they all have CCC 0.
186 #define LEAF_GEN(LEAF)	((LEAF)[0])
190 #define MINCCC		(0)
192 #define STOPPER		(0)
201  * Hangul decomposition (algorithm from Section 3.12 of Unicode 6.3.0)
203  * AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
204  * D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
206  * SBase = 0xAC00
207  * LBase = 0x1100
208  * VBase = 0x1161
209  * TBase = 0x11A7
237  *   if (TIndex == 0) {
246 #define SB	(0xAC00)
247 #define LB	(0x1100)
248 #define VB	(0x1161)
249 #define TB	(0x11A7)
289 	h[0] = '\0';  in utf8hangul()
312 	if (len == 0)  in utf8nlookup()
319 			if (--len == 0)  in utf8nlookup()
361 	 * codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is  in utf8nlookup()
365 	if (LEAF_CCC(trie) == DECOMPOSE && LEAF_STR(trie)[0] == HANGUL)  in utf8nlookup()
390 	size_t		ret = 0;  in utf8nlen()
418  * Returns -1 on error, 0 on success.
432 	u8c->slen = 0;  in utf8ncursor()
439 	if (len > 0 && (*s & 0xC0) == 0x80)  in utf8ncursor()
441 	return 0;  in utf8ncursor()
456  * and the function returns 0 in that case.
478 		if (u8c->p && *u8c->s == '\0') {  in utf8byte()
484 		if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) {  in utf8byte()
487 				return 0;  in utf8byte()
491 		} else if ((*u8c->s & 0xC0) == 0x80) {  in utf8byte()
511 		/* Characters that are too new have CCC 0. */  in utf8byte()
519 			/* Empty decomposition implies CCC 0. */  in utf8byte()
520 			if (*u8c->s == '\0') {  in utf8byte()
584 			u8c->slen = 0;  in utf8byte()