fs/unicode/mkutf8data.c

2985  *   u8c    : pointer to cursor.
2990 int utf8ncursor(struct utf8cursor *u8c, struct tree *tree, const char *s,
2997 	u8c->tree = tree;
2998 	u8c->s = s;
2999 	u8c->p = NULL;
3000 	u8c->ss = NULL;
3001 	u8c->sp = NULL;
3002 	u8c->len = len;
3003 	u8c->slen = 0;
3004 	u8c->ccc = STOPPER;
3005 	u8c->nccc = STOPPER;
3006 	u8c->unichar = 0;
3008 	if (u8c->len != len)
3020  *   u8c    : pointer to cursor.
3025 int utf8cursor(struct utf8cursor *u8c, struct tree *tree, const char *s)
3027 	return utf8ncursor(u8c, tree, s, (unsigned int)-1);
3031  * Get one byte from the normalized form of the string described by u8c.
3035  * The cursor keeps track of the location in the string in u8c->s.
3037  * u8c->p, and u8c->s is set to the start of the decomposition. Note
3038  * that bytes from a decomposition do not count against u8c->len.
3040  * Characters are emitted if they match the current CCC in u8c->ccc.
3041  * Hitting end-of-string while u8c->ccc == STOPPER means we're done,
3045  * values of u8c->s and u8c->p are stored in u8c->ss and u8c->sp at
3047  * emitted and stores it in u8c->nccc, the second pass emits the
3053  *  u8c->p  != NULL -> a decomposition is being scanned.
3054  *  u8c->ss != NULL -> this is a repeating scan.
3055  *  u8c->ccc == -1  -> this is the first scan of a repeating scan.
3057 int utf8byte(struct utf8cursor *u8c)
3064 		if (u8c->p && *u8c->s == '\0') {
3065 			u8c->s = u8c->p;
3066 			u8c->p = NULL;
3070 		if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) {
3072 			if (u8c->ccc == STOPPER)
3077 		} else if ((*u8c->s & 0xC0) == 0x80) {
3079 			if (!u8c->p)
3080 				u8c->len--;
3081 			return (unsigned char)*u8c->s++;
3085 		if (u8c->p) {
3086 			leaf = utf8lookup(u8c->tree, u8c->hangul, u8c->s);
3088 			leaf = utf8nlookup(u8c->tree, u8c->hangul,
3089 					   u8c->s, u8c->len);
3097 		if (ages[LEAF_GEN(leaf)] > u8c->tree->maxage) {
3100 			u8c->len -= utf8clen(u8c->s);
3101 			u8c->p = u8c->s + utf8clen(u8c->s);
3102 			u8c->s = LEAF_STR(leaf);
3104 			if (*u8c->s == '\0') {
3105 				if (u8c->ccc == STOPPER)
3110 			leaf = utf8lookup(u8c->tree, u8c->hangul, u8c->s);
3113 		u8c->unichar = utf8decode(u8c->s);
3119 		if (ccc != STOPPER && u8c->ccc < ccc && ccc < u8c->nccc)
3120 			u8c->nccc = ccc;
3126 		if (ccc == u8c->ccc) {
3127 			if (!u8c->p)
3128 				u8c->len--;
3129 			return (unsigned char)*u8c->s++;
3134 		if (u8c->nccc == STOPPER) {
3140 			assert(u8c->ccc == STOPPER);
3141 			u8c->ccc = MINCCC - 1;
3142 			u8c->nccc = ccc;
3143 			u8c->sp = u8c->p;
3144 			u8c->ss = u8c->s;
3145 			u8c->slen = u8c->len;
3146 			if (!u8c->p)
3147 				u8c->len -= utf8clen(u8c->s);
3148 			u8c->s += utf8clen(u8c->s);
3151 			if (!u8c->p)
3152 				u8c->len -= utf8clen(u8c->s);
3153 			u8c->s += utf8clen(u8c->s);
3154 		} else if (u8c->nccc != MAXCCC + 1) {
3156 			u8c->ccc = u8c->nccc;
3157 			u8c->nccc = MAXCCC + 1;
3158 			u8c->s = u8c->ss;
3159 			u8c->p = u8c->sp;
3160 			u8c->len = u8c->slen;
3163 			u8c->ccc = STOPPER;
3164 			u8c->nccc = STOPPER;
3165 			u8c->sp = NULL;
3166 			u8c->ss = NULL;
3167 			u8c->slen = 0;
3179 	struct utf8cursor u8c;
3184 	if (utf8cursor(&u8c, tree, s))
3186 	while ((c = utf8byte(&u8c)) > 0)
3199 	if (utf8cursor(&u8c, tree, s))
3201 	while ((c = utf8byte(&u8c)) > 0)