[696b405] | 1 | /*
|
---|
| 2 | * Copyright (c) 2025 Jiří Zárevúcky
|
---|
| 3 | * All rights reserved.
|
---|
| 4 | *
|
---|
| 5 | * Redistribution and use in source and binary forms, with or without
|
---|
| 6 | * modification, are permitted provided that the following conditions
|
---|
| 7 | * are met:
|
---|
| 8 | *
|
---|
| 9 | * - Redistributions of source code must retain the above copyright
|
---|
| 10 | * notice, this list of conditions and the following disclaimer.
|
---|
| 11 | * - Redistributions in binary form must reproduce the above copyright
|
---|
| 12 | * notice, this list of conditions and the following disclaimer in the
|
---|
| 13 | * documentation and/or other materials provided with the distribution.
|
---|
| 14 | * - The name of the author may not be used to endorse or promote products
|
---|
| 15 | * derived from this software without specific prior written permission.
|
---|
| 16 | *
|
---|
| 17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
---|
| 18 | * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
---|
| 19 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
---|
| 20 | * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
---|
| 21 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
---|
| 22 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
---|
| 23 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
---|
| 24 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
---|
| 25 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
---|
| 26 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
---|
| 27 | */
|
---|
| 28 |
|
---|
| 29 | #include <assert.h>
|
---|
| 30 | #include <errno.h>
|
---|
| 31 | #include <limits.h>
|
---|
| 32 | #include <stdbool.h>
|
---|
| 33 | #include <uchar.h>
|
---|
| 34 |
|
---|
| 35 | #if __STDC_HOSTED__
|
---|
| 36 | #include <fibril.h>
|
---|
| 37 | #endif
|
---|
| 38 |
|
---|
| 39 | static void _set_ilseq()
|
---|
| 40 | {
|
---|
| 41 | #ifdef errno
|
---|
| 42 | errno = EILSEQ;
|
---|
| 43 | #endif
|
---|
| 44 | }
|
---|
| 45 |
|
---|
| 46 | static bool _is_low_surrogate(char16_t c)
|
---|
| 47 | {
|
---|
| 48 | return c >= 0xDC00 && c < 0xE000;
|
---|
| 49 | }
|
---|
| 50 |
|
---|
| 51 | static bool _is_high_surrogate(char16_t c)
|
---|
| 52 | {
|
---|
| 53 | return c >= 0xD800 && c < 0xDC00;
|
---|
| 54 | }
|
---|
| 55 |
|
---|
| 56 | static bool _is_surrogate(char16_t c)
|
---|
| 57 | {
|
---|
| 58 | return c >= 0xD800 && c < 0xE000;
|
---|
| 59 | }
|
---|
| 60 |
|
---|
| 61 | #define UTF8_CONT(c, shift) (0x80 | (((c) >> (shift)) & 0x3F))
|
---|
| 62 |
|
---|
| 63 | size_t c32rtomb(char *s, char32_t c, mbstate_t *mb)
|
---|
| 64 | {
|
---|
| 65 | if (!s) {
|
---|
| 66 | // Equivalent to c32rtomb(buf, L’\0’, mb).
|
---|
| 67 | return 1;
|
---|
| 68 | }
|
---|
| 69 |
|
---|
| 70 | /* 1 byte encoding */
|
---|
| 71 | if (c < 0x80) {
|
---|
| 72 | s[0] = c;
|
---|
| 73 | return 1;
|
---|
| 74 | }
|
---|
| 75 |
|
---|
| 76 | /* 2 byte encoding */
|
---|
| 77 | if (c < 0x800) {
|
---|
| 78 | s[0] = 0b11000000 | (c >> 6);
|
---|
| 79 | s[1] = UTF8_CONT(c, 0);
|
---|
| 80 | return 2;
|
---|
| 81 | }
|
---|
| 82 |
|
---|
| 83 | /* 3 byte encoding */
|
---|
| 84 | if (c < 0x10000) {
|
---|
| 85 | if (_is_surrogate(c)) {
|
---|
| 86 | /* illegal range for an unicode code point */
|
---|
| 87 | _set_ilseq();
|
---|
| 88 | return UCHAR_ILSEQ;
|
---|
| 89 | }
|
---|
| 90 |
|
---|
| 91 | s[0] = 0b11100000 | (c >> 12);
|
---|
| 92 | s[1] = UTF8_CONT(c, 6);
|
---|
| 93 | s[2] = UTF8_CONT(c, 0);
|
---|
| 94 | return 3;
|
---|
| 95 | }
|
---|
| 96 |
|
---|
| 97 | /* 4 byte encoding */
|
---|
| 98 | if (c < 0x110000) {
|
---|
| 99 | s[0] = 0b11110000 | (c >> 18);
|
---|
| 100 | s[1] = UTF8_CONT(c, 12);
|
---|
| 101 | s[2] = UTF8_CONT(c, 6);
|
---|
| 102 | s[3] = UTF8_CONT(c, 0);
|
---|
| 103 | return 4;
|
---|
| 104 | }
|
---|
| 105 |
|
---|
| 106 | _set_ilseq();
|
---|
| 107 | return UCHAR_ILSEQ;
|
---|
| 108 | }
|
---|
| 109 |
|
---|
| 110 | size_t mbrtoc16(char16_t *c, const char *s, size_t n, mbstate_t *mb)
|
---|
| 111 | {
|
---|
| 112 | #if __STDC_HOSTED__
|
---|
| 113 | static fibril_local mbstate_t global_state = { };
|
---|
| 114 |
|
---|
| 115 | if (!mb)
|
---|
| 116 | mb = &global_state;
|
---|
| 117 | #else
|
---|
| 118 | assert(mb);
|
---|
| 119 | #endif
|
---|
| 120 |
|
---|
| 121 | char16_t dummy;
|
---|
| 122 |
|
---|
| 123 | if (!c)
|
---|
| 124 | c = &dummy;
|
---|
| 125 |
|
---|
| 126 | if (!s) {
|
---|
| 127 | /* Equivalent to mbrtoc16(NULL, "", 1, mb). */
|
---|
[f94a11f] | 128 | if (mb->state) {
|
---|
[696b405] | 129 | _set_ilseq();
|
---|
| 130 | return UCHAR_ILSEQ;
|
---|
| 131 | } else {
|
---|
| 132 | return 0;
|
---|
| 133 | }
|
---|
| 134 | }
|
---|
| 135 |
|
---|
[f94a11f] | 136 | if ((mb->state & 0xD000) == 0xD000) {
|
---|
[696b405] | 137 | /* mbstate_t contains the second surrogate character. */
|
---|
| 138 | /* mbrtoc32() will never set it to such value. */
|
---|
[f94a11f] | 139 | *c = mb->state;
|
---|
| 140 | mb->state = 0;
|
---|
[696b405] | 141 | return UCHAR_CONTINUED;
|
---|
| 142 | }
|
---|
| 143 |
|
---|
| 144 | char32_t c32 = 0;
|
---|
| 145 | size_t ret = mbrtoc32(&c32, s, n, mb);
|
---|
| 146 | if (ret < INT_MAX) {
|
---|
| 147 | if (c32 < 0x10000) {
|
---|
| 148 | *c = c32;
|
---|
| 149 | } else {
|
---|
| 150 | /* Encode UTF-16 surrogates. */
|
---|
[f94a11f] | 151 | mb->state = (c32 & 0x3FF) + 0xDC00;
|
---|
[696b405] | 152 | *c = (c32 >> 10) + 0xD7C0;
|
---|
| 153 | }
|
---|
| 154 | return ret;
|
---|
| 155 | }
|
---|
| 156 |
|
---|
| 157 | return ret;
|
---|
| 158 | }
|
---|
| 159 |
|
---|
| 160 | size_t c16rtomb(char *s, char16_t c, mbstate_t *mb)
|
---|
| 161 | {
|
---|
| 162 | #if __STDC_HOSTED__
|
---|
| 163 | static fibril_local mbstate_t global_state = { };
|
---|
| 164 |
|
---|
| 165 | if (!mb)
|
---|
| 166 | mb = &global_state;
|
---|
| 167 | #else
|
---|
| 168 | assert(mb);
|
---|
| 169 | #endif
|
---|
| 170 |
|
---|
| 171 | if (!s) {
|
---|
| 172 | // Equivalent to c16rtomb(buf, L’\0’, mb).
|
---|
[f94a11f] | 173 | if (mb->state) {
|
---|
[696b405] | 174 | _set_ilseq();
|
---|
| 175 | return UCHAR_ILSEQ;
|
---|
| 176 | } else {
|
---|
| 177 | return 1;
|
---|
| 178 | }
|
---|
| 179 | }
|
---|
| 180 |
|
---|
| 181 | if (!_is_surrogate(c)) {
|
---|
[f94a11f] | 182 | if (mb->state) {
|
---|
[696b405] | 183 | _set_ilseq();
|
---|
| 184 | return UCHAR_ILSEQ;
|
---|
| 185 | }
|
---|
| 186 |
|
---|
| 187 | return c32rtomb(s, c, mb);
|
---|
| 188 | }
|
---|
| 189 |
|
---|
[f94a11f] | 190 | if (!mb->state) {
|
---|
| 191 | mb->state = c;
|
---|
[696b405] | 192 | return 0;
|
---|
| 193 | }
|
---|
| 194 |
|
---|
| 195 | char32_t c32;
|
---|
| 196 |
|
---|
| 197 | /* Decode UTF-16 surrogates. */
|
---|
[f94a11f] | 198 | if (_is_low_surrogate(mb->state) && _is_high_surrogate(c)) {
|
---|
| 199 | c32 = ((c - 0xD7C0) << 10) | (mb->state - 0xDC00);
|
---|
| 200 | } else if (_is_high_surrogate(mb->state) && _is_low_surrogate(c)) {
|
---|
| 201 | c32 = ((mb->state - 0xD7C0) << 10) | (c - 0xDC00);
|
---|
[696b405] | 202 | } else {
|
---|
| 203 | _set_ilseq();
|
---|
| 204 | return UCHAR_ILSEQ;
|
---|
| 205 | }
|
---|
| 206 |
|
---|
[f94a11f] | 207 | mb->state = 0;
|
---|
[696b405] | 208 | return c32rtomb(s, c32, mb);
|
---|
| 209 | }
|
---|