Orange Pi5 kernel

Deprecated Linux kernel 5.10.110 for OrangePi 5/5B/5+ boards

3 Commits   0 Branches   0 Tags
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   3)  * Copyright (c) 2014 SGI.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   4)  * All rights reserved.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   5)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   6) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   7) #include "utf8n.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   8) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   9) struct utf8data {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  10) 	unsigned int maxage;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  11) 	unsigned int offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  12) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  13) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  14) #define __INCLUDED_FROM_UTF8NORM_C__
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  15) #include "utf8data.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  16) #undef __INCLUDED_FROM_UTF8NORM_C__
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  17) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  18) int utf8version_is_supported(u8 maj, u8 min, u8 rev)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  19) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  20) 	int i = ARRAY_SIZE(utf8agetab) - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  21) 	unsigned int sb_utf8version = UNICODE_AGE(maj, min, rev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  22) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  23) 	while (i >= 0 && utf8agetab[i] != 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  24) 		if (sb_utf8version == utf8agetab[i])
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  25) 			return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  26) 		i--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  27) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  28) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  29) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  30) EXPORT_SYMBOL(utf8version_is_supported);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  31) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  32) int utf8version_latest(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  33) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  34) 	return utf8vers;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  35) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  36) EXPORT_SYMBOL(utf8version_latest);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  37) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  38) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  39)  * UTF-8 valid ranges.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  40)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  41)  * The UTF-8 encoding spreads the bits of a 32bit word over several
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  42)  * bytes. This table gives the ranges that can be held and how they'd
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  43)  * be represented.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  44)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  45)  * 0x00000000 0x0000007F: 0xxxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  46)  * 0x00000000 0x000007FF: 110xxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  47)  * 0x00000000 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  48)  * 0x00000000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  49)  * 0x00000000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  50)  * 0x00000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  51)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  52)  * There is an additional requirement on UTF-8, in that only the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  53)  * shortest representation of a 32bit value is to be used.  A decoder
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  54)  * must not decode sequences that do not satisfy this requirement.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  55)  * Thus the allowed ranges have a lower bound.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  56)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  57)  * 0x00000000 0x0000007F: 0xxxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  58)  * 0x00000080 0x000007FF: 110xxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  59)  * 0x00000800 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  60)  * 0x00010000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  61)  * 0x00200000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  62)  * 0x04000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  63)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  64)  * Actual unicode characters are limited to the range 0x0 - 0x10FFFF,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  65)  * 17 planes of 65536 values.  This limits the sequences actually seen
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  66)  * even more, to just the following.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  67)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  68)  *          0 -     0x7F: 0                   - 0x7F
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  69)  *       0x80 -    0x7FF: 0xC2 0x80           - 0xDF 0xBF
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  70)  *      0x800 -   0xFFFF: 0xE0 0xA0 0x80      - 0xEF 0xBF 0xBF
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  71)  *    0x10000 - 0x10FFFF: 0xF0 0x90 0x80 0x80 - 0xF4 0x8F 0xBF 0xBF
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  72)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  73)  * Within those ranges the surrogates 0xD800 - 0xDFFF are not allowed.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  74)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  75)  * Note that the longest sequence seen with valid usage is 4 bytes,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  76)  * the same a single UTF-32 character.  This makes the UTF-8
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  77)  * representation of Unicode strictly smaller than UTF-32.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  78)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  79)  * The shortest sequence requirement was introduced by:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  80)  *    Corrigendum #1: UTF-8 Shortest Form
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  81)  * It can be found here:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  82)  *    http://www.unicode.org/versions/corrigendum1.html
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  83)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  84)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  85) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  86) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  87)  * Return the number of bytes used by the current UTF-8 sequence.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  88)  * Assumes the input points to the first byte of a valid UTF-8
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  89)  * sequence.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  90)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  91) static inline int utf8clen(const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  92) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  93) 	unsigned char c = *s;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  94) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  95) 	return 1 + (c >= 0xC0) + (c >= 0xE0) + (c >= 0xF0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  96) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  97) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  98) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  99)  * Decode a 3-byte UTF-8 sequence.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) static unsigned int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) utf8decode3(const char *str)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) 	unsigned int		uc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) 	uc = *str++ & 0x0F;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) 	uc <<= 6;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) 	uc |= *str++ & 0x3F;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) 	uc <<= 6;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) 	uc |= *str++ & 0x3F;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) 	return uc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116)  * Encode a 3-byte UTF-8 sequence.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) static int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) utf8encode3(char *str, unsigned int val)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) 	str[2] = (val & 0x3F) | 0x80;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) 	val >>= 6;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) 	str[1] = (val & 0x3F) | 0x80;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) 	val >>= 6;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) 	str[0] = val | 0xE0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) 	return 3;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131)  * utf8trie_t
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133)  * A compact binary tree, used to decode UTF-8 characters.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135)  * Internal nodes are one byte for the node itself, and up to three
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136)  * bytes for an offset into the tree.  The first byte contains the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137)  * following information:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138)  *  NEXTBYTE  - flag        - advance to next byte if set
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139)  *  BITNUM    - 3 bit field - the bit number to tested
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140)  *  OFFLEN    - 2 bit field - number of bytes in the offset
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141)  * if offlen == 0 (non-branching node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142)  *  RIGHTPATH - 1 bit field - set if the following node is for the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143)  *                            right-hand path (tested bit is set)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144)  *  TRIENODE  - 1 bit field - set if the following node is an internal
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145)  *                            node, otherwise it is a leaf node
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146)  * if offlen != 0 (branching node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147)  *  LEFTNODE  - 1 bit field - set if the left-hand node is internal
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148)  *  RIGHTNODE - 1 bit field - set if the right-hand node is internal
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150)  * Due to the way utf8 works, there cannot be branching nodes with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151)  * NEXTBYTE set, and moreover those nodes always have a righthand
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152)  * descendant.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) typedef const unsigned char utf8trie_t;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) #define BITNUM		0x07
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) #define NEXTBYTE	0x08
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) #define OFFLEN		0x30
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) #define OFFLEN_SHIFT	4
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) #define RIGHTPATH	0x40
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) #define TRIENODE	0x80
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) #define RIGHTNODE	0x40
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) #define LEFTNODE	0x80
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165)  * utf8leaf_t
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167)  * The leaves of the trie are embedded in the trie, and so the same
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168)  * underlying datatype: unsigned char.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170)  * leaf[0]: The unicode version, stored as a generation number that is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171)  *          an index into utf8agetab[].  With this we can filter code
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172)  *          points based on the unicode version in which they were
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173)  *          defined.  The CCC of a non-defined code point is 0.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174)  * leaf[1]: Canonical Combining Class. During normalization, we need
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175)  *          to do a stable sort into ascending order of all characters
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176)  *          with a non-zero CCC that occur between two characters with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177)  *          a CCC of 0, or at the begin or end of a string.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178)  *          The unicode standard guarantees that all CCC values are
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179)  *          between 0 and 254 inclusive, which leaves 255 available as
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180)  *          a special value.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181)  *          Code points with CCC 0 are known as stoppers.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182)  * leaf[2]: Decomposition. If leaf[1] == 255, then leaf[2] is the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183)  *          start of a NUL-terminated string that is the decomposition
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184)  *          of the character.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185)  *          The CCC of a decomposable character is the same as the CCC
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186)  *          of the first character of its decomposition.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187)  *          Some characters decompose as the empty string: these are
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188)  *          characters with the Default_Ignorable_Code_Point property.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189)  *          These do affect normalization, as they all have CCC 0.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191)  * The decompositions in the trie have been fully expanded, with the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192)  * exception of Hangul syllables, which are decomposed algorithmically.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194)  * Casefolding, if applicable, is also done using decompositions.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196)  * The trie is constructed in such a way that leaves exist for all
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197)  * UTF-8 sequences that match the criteria from the "UTF-8 valid
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198)  * ranges" comment above, and only for those sequences.  Therefore a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199)  * lookup in the trie can be used to validate the UTF-8 input.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) typedef const unsigned char utf8leaf_t;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) #define LEAF_GEN(LEAF)	((LEAF)[0])
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) #define LEAF_CCC(LEAF)	((LEAF)[1])
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) #define LEAF_STR(LEAF)	((const char *)((LEAF) + 2))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) #define MINCCC		(0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) #define MAXCCC		(254)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) #define STOPPER		(0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) #define	DECOMPOSE	(255)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) /* Marker for hangul syllable decomposition. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) #define HANGUL		((char)(255))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) /* Size of the synthesized leaf used for Hangul syllable decomposition. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) #define UTF8HANGULLEAF	(12)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218)  * Hangul decomposition (algorithm from Section 3.12 of Unicode 6.3.0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220)  * AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221)  * D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223)  * SBase = 0xAC00
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224)  * LBase = 0x1100
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225)  * VBase = 0x1161
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226)  * TBase = 0x11A7
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227)  * LCount = 19
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228)  * VCount = 21
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229)  * TCount = 28
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230)  * NCount = 588 (VCount * TCount)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231)  * SCount = 11172 (LCount * NCount)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233)  * Decomposition:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234)  *   SIndex = s - SBase
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236)  * LV (Canonical/Full)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237)  *   LIndex = SIndex / NCount
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238)  *   VIndex = (Sindex % NCount) / TCount
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239)  *   LPart = LBase + LIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240)  *   VPart = VBase + VIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242)  * LVT (Canonical)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243)  *   LVIndex = (SIndex / TCount) * TCount
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244)  *   TIndex = (Sindex % TCount)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245)  *   LVPart = SBase + LVIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246)  *   TPart = TBase + TIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248)  * LVT (Full)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249)  *   LIndex = SIndex / NCount
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250)  *   VIndex = (Sindex % NCount) / TCount
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251)  *   TIndex = (Sindex % TCount)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252)  *   LPart = LBase + LIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253)  *   VPart = VBase + VIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254)  *   if (TIndex == 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255)  *          d = <LPart, VPart>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256)  *   } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257)  *          TPart = TBase + TIndex
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258)  *          d = <LPart, TPart, VPart>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259)  *   }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) /* Constants */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) #define SB	(0xAC00)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) #define LB	(0x1100)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) #define VB	(0x1161)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) #define TB	(0x11A7)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) #define LC	(19)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) #define VC	(21)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) #define TC	(28)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) #define NC	(VC * TC)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) #define SC	(LC * NC)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) /* Algorithmic decomposition of hangul syllable. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) static utf8leaf_t *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) utf8hangul(const char *str, unsigned char *hangul)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) 	unsigned int	si;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) 	unsigned int	li;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279) 	unsigned int	vi;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) 	unsigned int	ti;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) 	unsigned char	*h;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) 	/* Calculate the SI, LI, VI, and TI values. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) 	si = utf8decode3(str) - SB;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) 	li = si / NC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) 	vi = (si % NC) / TC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) 	ti = si % TC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) 	/* Fill in base of leaf. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) 	h = hangul;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) 	LEAF_GEN(h) = 2;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) 	LEAF_CCC(h) = DECOMPOSE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) 	h += 2;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) 	/* Add LPart, a 3-byte UTF-8 sequence. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) 	h += utf8encode3((char *)h, li + LB);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) 	/* Add VPart, a 3-byte UTF-8 sequence. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) 	h += utf8encode3((char *)h, vi + VB);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) 	/* Add TPart if required, also a 3-byte UTF-8 sequence. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) 	if (ti)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) 		h += utf8encode3((char *)h, ti + TB);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) 	/* Terminate string. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) 	h[0] = '\0';
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) 	return hangul;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312)  * Use trie to scan s, touching at most len bytes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313)  * Returns the leaf if one exists, NULL otherwise.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315)  * A non-NULL return guarantees that the UTF-8 sequence starting at s
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316)  * is well-formed and corresponds to a known unicode code point.  The
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317)  * shorthand for this will be "is valid UTF-8 unicode".
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) static utf8leaf_t *utf8nlookup(const struct utf8data *data,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) 			       unsigned char *hangul, const char *s, size_t len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) 	utf8trie_t	*trie = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) 	int		offlen;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) 	int		offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) 	int		mask;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) 	int		node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) 		return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) 	if (len == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) 		return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) 	trie = utf8data + data->offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) 	node = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) 	while (node) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) 		offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) 		if (*trie & NEXTBYTE) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) 			if (--len == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) 				return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) 			s++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) 		mask = 1 << (*trie & BITNUM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) 		if (*s & mask) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) 			/* Right leg */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) 			if (offlen) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) 				/* Right node at offset of trie */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) 				node = (*trie & RIGHTNODE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) 				offset = trie[offlen];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) 				while (--offlen) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) 					offset <<= 8;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) 					offset |= trie[offlen];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) 				}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) 				trie += offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) 			} else if (*trie & RIGHTPATH) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) 				/* Right node after this node */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) 				node = (*trie & TRIENODE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) 				trie++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) 			} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) 				/* No right node. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) 				return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) 			/* Left leg */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) 			if (offlen) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) 				/* Left node after this node. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) 				node = (*trie & LEFTNODE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) 				trie += offlen + 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) 			} else if (*trie & RIGHTPATH) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) 				/* No left node. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) 				return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) 			} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) 				/* Left node after this node */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) 				node = (*trie & TRIENODE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) 				trie++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) 	 * Hangul decomposition is done algorithmically. These are the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) 	 * codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) 	 * always 3 bytes long, so s has been advanced twice, and the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382) 	 * start of the sequence is at s-2.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) 	if (LEAF_CCC(trie) == DECOMPOSE && LEAF_STR(trie)[0] == HANGUL)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) 		trie = utf8hangul(s - 2, hangul);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) 	return trie;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390)  * Use trie to scan s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391)  * Returns the leaf if one exists, NULL otherwise.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393)  * Forwards to utf8nlookup().
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) static utf8leaf_t *utf8lookup(const struct utf8data *data,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) 			      unsigned char *hangul, const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) 	return utf8nlookup(data, hangul, s, (size_t)-1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402)  * Maximum age of any character in s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404)  * Return 0 if only non-assigned code points are used.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) int utf8agemax(const struct utf8data *data, const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) 	int		age = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410) 	int		leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) 	while (*s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) 		leaf = utf8lookup(data, hangul, s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) 		leaf_age = utf8agetab[LEAF_GEN(leaf)];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422) 		if (leaf_age <= data->maxage && leaf_age > age)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) 			age = leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426) 	return age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) EXPORT_SYMBOL(utf8agemax);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431)  * Minimum age of any character in s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433)  * Return 0 if non-assigned code points are used.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) int utf8agemin(const struct utf8data *data, const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) 	int		age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) 	int		leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) 	age = data->maxage;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445) 	while (*s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) 		leaf = utf8lookup(data, hangul, s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449) 		leaf_age = utf8agetab[LEAF_GEN(leaf)];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) 		if (leaf_age <= data->maxage && leaf_age < age)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451) 			age = leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454) 	return age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) EXPORT_SYMBOL(utf8agemin);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459)  * Maximum age of any character in s, touch at most len bytes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462) int utf8nagemax(const struct utf8data *data, const char *s, size_t len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) 	int		age = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) 	int		leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) 	while (len && *s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473) 		leaf = utf8nlookup(data, hangul, s, len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) 		leaf_age = utf8agetab[LEAF_GEN(leaf)];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477) 		if (leaf_age <= data->maxage && leaf_age > age)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478) 			age = leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) 		len -= utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) 	return age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) EXPORT_SYMBOL(utf8nagemax);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487)  * Maximum age of any character in s, touch at most len bytes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) int utf8nagemin(const struct utf8data *data, const char *s, size_t len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) 	int		leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494) 	int		age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) 	age = data->maxage;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) 	while (len && *s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501) 		leaf = utf8nlookup(data, hangul, s, len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) 		leaf_age = utf8agetab[LEAF_GEN(leaf)];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505) 		if (leaf_age <= data->maxage && leaf_age < age)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506) 			age = leaf_age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) 		len -= utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) 	return age;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) EXPORT_SYMBOL(utf8nagemin);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515)  * Length of the normalization of s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518)  * A string of Default_Ignorable_Code_Point has length 0.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) ssize_t utf8len(const struct utf8data *data, const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) 	size_t		ret = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) 	while (*s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) 		leaf = utf8lookup(data, hangul, s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) 		if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533) 			ret += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) 		else if (LEAF_CCC(leaf) == DECOMPOSE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) 			ret += strlen(LEAF_STR(leaf));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) 		else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) 			ret += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) 	return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542) EXPORT_SYMBOL(utf8len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545)  * Length of the normalization of s, touch at most len bytes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546)  * Return -1 if s is not valid UTF-8 unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) 	utf8leaf_t	*leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) 	size_t		ret = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552) 	unsigned char	hangul[UTF8HANGULLEAF];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) 	while (len && *s) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557) 		leaf = utf8nlookup(data, hangul, s, len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) 		if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) 			ret += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562) 		else if (LEAF_CCC(leaf) == DECOMPOSE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) 			ret += strlen(LEAF_STR(leaf));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) 		else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) 			ret += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) 		len -= utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) 		s += utf8clen(s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) 	return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571) EXPORT_SYMBOL(utf8nlen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574)  * Set up an utf8cursor for use by utf8byte().
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576)  *   u8c    : pointer to cursor.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577)  *   data   : const struct utf8data to use for normalization.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578)  *   s      : string.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579)  *   len    : length of s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581)  * Returns -1 on error, 0 on success.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583) int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584) 		const char *s, size_t len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586) 	if (!data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) 	if (!s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590) 	u8c->data = data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) 	u8c->s = s;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592) 	u8c->p = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) 	u8c->ss = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) 	u8c->sp = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595) 	u8c->len = len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596) 	u8c->slen = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597) 	u8c->ccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598) 	u8c->nccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599) 	/* Check we didn't clobber the maximum length. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600) 	if (u8c->len != len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) 	/* The first byte of s may not be an utf8 continuation. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603) 	if (len > 0 && (*s & 0xC0) == 0x80)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) 		return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) EXPORT_SYMBOL(utf8ncursor);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610)  * Set up an utf8cursor for use by utf8byte().
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612)  *   u8c    : pointer to cursor.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613)  *   data   : const struct utf8data to use for normalization.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614)  *   s      : NUL-terminated string.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616)  * Returns -1 on error, 0 on success.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618) int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619) 	       const char *s)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621) 	return utf8ncursor(u8c, data, s, (unsigned int)-1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623) EXPORT_SYMBOL(utf8cursor);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626)  * Get one byte from the normalized form of the string described by u8c.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628)  * Returns the byte cast to an unsigned char on succes, and -1 on failure.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630)  * The cursor keeps track of the location in the string in u8c->s.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631)  * When a character is decomposed, the current location is stored in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632)  * u8c->p, and u8c->s is set to the start of the decomposition. Note
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633)  * that bytes from a decomposition do not count against u8c->len.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635)  * Characters are emitted if they match the current CCC in u8c->ccc.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636)  * Hitting end-of-string while u8c->ccc == STOPPER means we're done,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637)  * and the function returns 0 in that case.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639)  * Sorting by CCC is done by repeatedly scanning the string.  The
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640)  * values of u8c->s and u8c->p are stored in u8c->ss and u8c->sp at
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641)  * the start of the scan.  The first pass finds the lowest CCC to be
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642)  * emitted and stores it in u8c->nccc, the second pass emits the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643)  * characters with this CCC and finds the next lowest CCC. This limits
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644)  * the number of passes to 1 + the number of different CCCs in the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645)  * sequence being scanned.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647)  * Therefore:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648)  *  u8c->p  != NULL -> a decomposition is being scanned.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649)  *  u8c->ss != NULL -> this is a repeating scan.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650)  *  u8c->ccc == -1   -> this is the first scan of a repeating scan.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652) int utf8byte(struct utf8cursor *u8c)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) 	utf8leaf_t *leaf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) 	int ccc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 657) 	for (;;) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 658) 		/* Check for the end of a decomposed character. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 659) 		if (u8c->p && *u8c->s == '\0') {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 660) 			u8c->s = u8c->p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 661) 			u8c->p = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 662) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 663) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 664) 		/* Check for end-of-string. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 665) 		if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 666) 			/* There is no next byte. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 667) 			if (u8c->ccc == STOPPER)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 668) 				return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 669) 			/* End-of-string during a scan counts as a stopper. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 670) 			ccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 671) 			goto ccc_mismatch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 672) 		} else if ((*u8c->s & 0xC0) == 0x80) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 673) 			/* This is a continuation of the current character. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 674) 			if (!u8c->p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 675) 				u8c->len--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 676) 			return (unsigned char)*u8c->s++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 677) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 678) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 679) 		/* Look up the data for the current character. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 680) 		if (u8c->p) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 681) 			leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 682) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 683) 			leaf = utf8nlookup(u8c->data, u8c->hangul,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 684) 					   u8c->s, u8c->len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 685) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 686) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 687) 		/* No leaf found implies that the input is a binary blob. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 688) 		if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 689) 			return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 690) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 691) 		ccc = LEAF_CCC(leaf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 692) 		/* Characters that are too new have CCC 0. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 693) 		if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 694) 			ccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 695) 		} else if (ccc == DECOMPOSE) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 696) 			u8c->len -= utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 697) 			u8c->p = u8c->s + utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 698) 			u8c->s = LEAF_STR(leaf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 699) 			/* Empty decomposition implies CCC 0. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 700) 			if (*u8c->s == '\0') {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 701) 				if (u8c->ccc == STOPPER)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 702) 					continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 703) 				ccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 704) 				goto ccc_mismatch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 705) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 706) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 707) 			leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 708) 			if (!leaf)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 709) 				return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 710) 			ccc = LEAF_CCC(leaf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 711) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 712) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 713) 		/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 714) 		 * If this is not a stopper, then see if it updates
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 715) 		 * the next canonical class to be emitted.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 716) 		 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 717) 		if (ccc != STOPPER && u8c->ccc < ccc && ccc < u8c->nccc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 718) 			u8c->nccc = ccc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 719) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 720) 		/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 721) 		 * Return the current byte if this is the current
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 722) 		 * combining class.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 723) 		 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 724) 		if (ccc == u8c->ccc) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 725) 			if (!u8c->p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 726) 				u8c->len--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 727) 			return (unsigned char)*u8c->s++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 728) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 729) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 730) 		/* Current combining class mismatch. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 731) ccc_mismatch:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 732) 		if (u8c->nccc == STOPPER) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 733) 			/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 734) 			 * Scan forward for the first canonical class
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 735) 			 * to be emitted.  Save the position from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 736) 			 * which to restart.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 737) 			 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 738) 			u8c->ccc = MINCCC - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 739) 			u8c->nccc = ccc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 740) 			u8c->sp = u8c->p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 741) 			u8c->ss = u8c->s;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 742) 			u8c->slen = u8c->len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 743) 			if (!u8c->p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 744) 				u8c->len -= utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 745) 			u8c->s += utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 746) 		} else if (ccc != STOPPER) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 747) 			/* Not a stopper, and not the ccc we're emitting. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 748) 			if (!u8c->p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 749) 				u8c->len -= utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 750) 			u8c->s += utf8clen(u8c->s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 751) 		} else if (u8c->nccc != MAXCCC + 1) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 752) 			/* At a stopper, restart for next ccc. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 753) 			u8c->ccc = u8c->nccc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 754) 			u8c->nccc = MAXCCC + 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 755) 			u8c->s = u8c->ss;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 756) 			u8c->p = u8c->sp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 757) 			u8c->len = u8c->slen;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 758) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 759) 			/* All done, proceed from here. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 760) 			u8c->ccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 761) 			u8c->nccc = STOPPER;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 762) 			u8c->sp = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 763) 			u8c->ss = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 764) 			u8c->slen = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 765) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 766) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 767) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 768) EXPORT_SYMBOL(utf8byte);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 769) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 770) const struct utf8data *utf8nfdi(unsigned int maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 771) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 772) 	int i = ARRAY_SIZE(utf8nfdidata) - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 773) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 774) 	while (maxage < utf8nfdidata[i].maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 775) 		i--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 776) 	if (maxage > utf8nfdidata[i].maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 777) 		return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 778) 	return &utf8nfdidata[i];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 779) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 780) EXPORT_SYMBOL(utf8nfdi);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 781) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 782) const struct utf8data *utf8nfdicf(unsigned int maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 783) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 784) 	int i = ARRAY_SIZE(utf8nfdicfdata) - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 785) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 786) 	while (maxage < utf8nfdicfdata[i].maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 787) 		i--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 788) 	if (maxage > utf8nfdicfdata[i].maxage)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 789) 		return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 790) 	return &utf8nfdicfdata[i];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 791) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 792) EXPORT_SYMBOL(utf8nfdicf);