Lines Matching +full:nc +full:- +full:si
1 // SPDX-License-Identifier: GPL-2.0-only
20 int i = ARRAY_SIZE(utf8agetab) - 1; in utf8version_is_supported()
26 i--; in utf8version_is_supported()
39 * UTF-8 valid ranges.
41 * The UTF-8 encoding spreads the bits of a 32bit word over several
52 * There is an additional requirement on UTF-8, in that only the
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.
76 * the same a single UTF-32 character. This makes the UTF-8
77 * representation of Unicode strictly smaller than UTF-32.
80 * Corrigendum #1: UTF-8 Shortest Form
87 * Return the number of bytes used by the current UTF-8 sequence.
88 * Assumes the input points to the first byte of a valid UTF-8
99 * Decode a 3-byte UTF-8 sequence.
116 * Encode a 3-byte UTF-8 sequence.
133 * A compact binary tree, used to decode UTF-8 characters.
138 * NEXTBYTE - flag - advance to next byte if set
139 * BITNUM - 3 bit field - the bit number to tested
140 * OFFLEN - 2 bit field - number of bytes in the offset
141 * if offlen == 0 (non-branching node)
142 * RIGHTPATH - 1 bit field - set if the following node is for the
143 * right-hand path (tested bit is set)
144 * TRIENODE - 1 bit field - set if the following node is an internal
147 * LEFTNODE - 1 bit field - set if the left-hand node is internal
148 * RIGHTNODE - 1 bit field - set if the right-hand node is internal
173 * defined. The CCC of a non-defined code point is 0.
176 * with a non-zero CCC that occur between two characters with
183 * start of a NUL-terminated string that is the decomposition
197 * UTF-8 sequences that match the criteria from the "UTF-8 valid
199 * lookup in the trie can be used to validate the UTF-8 input.
234 * SIndex = s - SBase
270 #define NC (VC * TC) macro
271 #define SC (LC * NC)
277 unsigned int si; in utf8hangul() local
283 /* Calculate the SI, LI, VI, and TI values. */ in utf8hangul()
284 si = utf8decode3(str) - SB; in utf8hangul()
285 li = si / NC; in utf8hangul()
286 vi = (si % NC) / TC; in utf8hangul()
287 ti = si % TC; in utf8hangul()
295 /* Add LPart, a 3-byte UTF-8 sequence. */ in utf8hangul()
298 /* Add VPart, a 3-byte UTF-8 sequence. */ in utf8hangul()
301 /* Add TPart if required, also a 3-byte UTF-8 sequence. */ in utf8hangul()
315 * A non-NULL return guarantees that the UTF-8 sequence starting at s
316 * is well-formed and corresponds to a known unicode code point. The
317 * shorthand for this will be "is valid UTF-8 unicode".
333 trie = utf8data + data->offset; in utf8nlookup()
338 if (--len == 0) in utf8nlookup()
349 while (--offlen) { in utf8nlookup()
380 * codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is in utf8nlookup()
382 * start of the sequence is at s-2. in utf8nlookup()
385 trie = utf8hangul(s - 2, hangul); in utf8nlookup()
398 return utf8nlookup(data, hangul, s, (size_t)-1); in utf8lookup()
403 * Return -1 if s is not valid UTF-8 unicode.
404 * Return 0 if only non-assigned code points are used.
414 return -1; in utf8agemax()
419 return -1; in utf8agemax()
422 if (leaf_age <= data->maxage && leaf_age > age) in utf8agemax()
432 * Return -1 if s is not valid UTF-8 unicode.
433 * Return 0 if non-assigned code points are used.
443 return -1; in utf8agemin()
444 age = data->maxage; in utf8agemin()
448 return -1; in utf8agemin()
450 if (leaf_age <= data->maxage && leaf_age < age) in utf8agemin()
460 * Return -1 if s is not valid UTF-8 unicode.
470 return -1; in utf8nagemax()
475 return -1; in utf8nagemax()
477 if (leaf_age <= data->maxage && leaf_age > age) in utf8nagemax()
479 len -= utf8clen(s); in utf8nagemax()
488 * Return -1 if s is not valid UTF-8 unicode.
498 return -1; in utf8nagemin()
499 age = data->maxage; in utf8nagemin()
503 return -1; in utf8nagemin()
505 if (leaf_age <= data->maxage && leaf_age < age) in utf8nagemin()
507 len -= utf8clen(s); in utf8nagemin()
516 * Return -1 if s is not valid UTF-8 unicode.
527 return -1; in utf8len()
531 return -1; in utf8len()
532 if (utf8agetab[LEAF_GEN(leaf)] > data->maxage) in utf8len()
546 * Return -1 if s is not valid UTF-8 unicode.
555 return -1; in utf8nlen()
559 return -1; in utf8nlen()
560 if (utf8agetab[LEAF_GEN(leaf)] > data->maxage) in utf8nlen()
566 len -= utf8clen(s); in utf8nlen()
581 * Returns -1 on error, 0 on success.
587 return -1; in utf8ncursor()
589 return -1; in utf8ncursor()
590 u8c->data = data; in utf8ncursor()
591 u8c->s = s; in utf8ncursor()
592 u8c->p = NULL; in utf8ncursor()
593 u8c->ss = NULL; in utf8ncursor()
594 u8c->sp = NULL; in utf8ncursor()
595 u8c->len = len; in utf8ncursor()
596 u8c->slen = 0; in utf8ncursor()
597 u8c->ccc = STOPPER; in utf8ncursor()
598 u8c->nccc = STOPPER; in utf8ncursor()
600 if (u8c->len != len) in utf8ncursor()
601 return -1; in utf8ncursor()
604 return -1; in utf8ncursor()
614 * s : NUL-terminated string.
616 * Returns -1 on error, 0 on success.
621 return utf8ncursor(u8c, data, s, (unsigned int)-1); in utf8cursor()
628 * Returns the byte cast to an unsigned char on succes, and -1 on failure.
630 * The cursor keeps track of the location in the string in u8c->s.
632 * u8c->p, and u8c->s is set to the start of the decomposition. Note
633 * that bytes from a decomposition do not count against u8c->len.
635 * Characters are emitted if they match the current CCC in u8c->ccc.
636 * Hitting end-of-string while u8c->ccc == STOPPER means we're done,
640 * values of u8c->s and u8c->p are stored in u8c->ss and u8c->sp at
642 * emitted and stores it in u8c->nccc, the second pass emits the
648 * u8c->p != NULL -> a decomposition is being scanned.
649 * u8c->ss != NULL -> this is a repeating scan.
650 * u8c->ccc == -1 -> this is the first scan of a repeating scan.
659 if (u8c->p && *u8c->s == '\0') { in utf8byte()
660 u8c->s = u8c->p; in utf8byte()
661 u8c->p = NULL; in utf8byte()
664 /* Check for end-of-string. */ in utf8byte()
665 if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) { in utf8byte()
667 if (u8c->ccc == STOPPER) in utf8byte()
669 /* End-of-string during a scan counts as a stopper. */ in utf8byte()
672 } else if ((*u8c->s & 0xC0) == 0x80) { in utf8byte()
674 if (!u8c->p) in utf8byte()
675 u8c->len--; in utf8byte()
676 return (unsigned char)*u8c->s++; in utf8byte()
680 if (u8c->p) { in utf8byte()
681 leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s); in utf8byte()
683 leaf = utf8nlookup(u8c->data, u8c->hangul, in utf8byte()
684 u8c->s, u8c->len); in utf8byte()
689 return -1; in utf8byte()
693 if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) { in utf8byte()
696 u8c->len -= utf8clen(u8c->s); in utf8byte()
697 u8c->p = u8c->s + utf8clen(u8c->s); in utf8byte()
698 u8c->s = LEAF_STR(leaf); in utf8byte()
700 if (*u8c->s == '\0') { in utf8byte()
701 if (u8c->ccc == STOPPER) in utf8byte()
707 leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s); in utf8byte()
709 return -1; in utf8byte()
717 if (ccc != STOPPER && u8c->ccc < ccc && ccc < u8c->nccc) in utf8byte()
718 u8c->nccc = ccc; in utf8byte()
724 if (ccc == u8c->ccc) { in utf8byte()
725 if (!u8c->p) in utf8byte()
726 u8c->len--; in utf8byte()
727 return (unsigned char)*u8c->s++; in utf8byte()
732 if (u8c->nccc == STOPPER) { in utf8byte()
738 u8c->ccc = MINCCC - 1; in utf8byte()
739 u8c->nccc = ccc; in utf8byte()
740 u8c->sp = u8c->p; in utf8byte()
741 u8c->ss = u8c->s; in utf8byte()
742 u8c->slen = u8c->len; in utf8byte()
743 if (!u8c->p) in utf8byte()
744 u8c->len -= utf8clen(u8c->s); in utf8byte()
745 u8c->s += utf8clen(u8c->s); in utf8byte()
748 if (!u8c->p) in utf8byte()
749 u8c->len -= utf8clen(u8c->s); in utf8byte()
750 u8c->s += utf8clen(u8c->s); in utf8byte()
751 } else if (u8c->nccc != MAXCCC + 1) { in utf8byte()
753 u8c->ccc = u8c->nccc; in utf8byte()
754 u8c->nccc = MAXCCC + 1; in utf8byte()
755 u8c->s = u8c->ss; in utf8byte()
756 u8c->p = u8c->sp; in utf8byte()
757 u8c->len = u8c->slen; in utf8byte()
760 u8c->ccc = STOPPER; in utf8byte()
761 u8c->nccc = STOPPER; in utf8byte()
762 u8c->sp = NULL; in utf8byte()
763 u8c->ss = NULL; in utf8byte()
764 u8c->slen = 0; in utf8byte()
772 int i = ARRAY_SIZE(utf8nfdidata) - 1; in utf8nfdi()
775 i--; in utf8nfdi()
784 int i = ARRAY_SIZE(utf8nfdicfdata) - 1; in utf8nfdicf()
787 i--; in utf8nfdicf()