H. Peter Anvin | 9e6747c | 2009-06-28 17:13:04 -0700 | [diff] [blame] | 1 | /* ----------------------------------------------------------------------- * |
| 2 | * |
| 3 | * Copyright 1996-2009 The NASM Authors - All Rights Reserved |
| 4 | * See the file AUTHORS included with the NASM distribution for |
| 5 | * the specific copyright holders. |
| 6 | * |
| 7 | * Redistribution and use in source and binary forms, with or without |
| 8 | * modification, are permitted provided that the following |
| 9 | * conditions are met: |
| 10 | * |
| 11 | * * Redistributions of source code must retain the above copyright |
| 12 | * notice, this list of conditions and the following disclaimer. |
| 13 | * * Redistributions in binary form must reproduce the above |
| 14 | * copyright notice, this list of conditions and the following |
| 15 | * disclaimer in the documentation and/or other materials provided |
| 16 | * with the distribution. |
| 17 | * |
| 18 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND |
| 19 | * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, |
| 20 | * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF |
| 21 | * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
| 22 | * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR |
| 23 | * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 24 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
| 25 | * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
| 26 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
| 27 | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
| 28 | * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR |
| 29 | * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, |
| 30 | * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 31 | * |
| 32 | * ----------------------------------------------------------------------- */ |
| 33 | |
H. Peter Anvin | 518df30 | 2008-06-14 16:53:48 -0700 | [diff] [blame] | 34 | /* |
| 35 | * strfunc.c |
| 36 | * |
| 37 | * String transformation functions |
| 38 | */ |
| 39 | |
| 40 | #include "nasmlib.h" |
| 41 | #include "nasm.h" |
| 42 | |
| 43 | /* |
| 44 | * Convert a string in UTF-8 format to UTF-16LE |
| 45 | */ |
| 46 | static size_t utf8_to_16le(uint8_t *str, size_t len, char *op) |
| 47 | { |
| 48 | #define EMIT(x) do { if (op) { WRITESHORT(op,x); } outlen++; } while(0) |
| 49 | |
| 50 | size_t outlen = 0; |
| 51 | int expect = 0; |
| 52 | uint8_t c; |
| 53 | uint32_t v = 0, vmin = 0; |
| 54 | |
| 55 | while (len--) { |
| 56 | c = *str++; |
| 57 | |
| 58 | if (expect) { |
| 59 | if ((c & 0xc0) != 0x80) { |
| 60 | expect = 0; |
| 61 | return -1; |
| 62 | } else { |
| 63 | v = (v << 6) | (c & 0x3f); |
| 64 | if (!--expect) { |
| 65 | if (v < vmin || v > 0x10ffff || |
| 66 | (v >= 0xd800 && v <= 0xdfff)) { |
| 67 | return -1; |
| 68 | } else if (v > 0xffff) { |
| 69 | v -= 0x10000; |
| 70 | EMIT(0xd800 | (v >> 10)); |
| 71 | EMIT(0xdc00 | (v & 0x3ff)); |
| 72 | } else { |
| 73 | EMIT(v); |
| 74 | } |
| 75 | } |
| 76 | continue; |
| 77 | } |
| 78 | } |
| 79 | |
| 80 | if (c < 0x80) { |
| 81 | EMIT(c); |
H. Peter Anvin | 503e71d | 2008-06-14 21:07:09 -0700 | [diff] [blame] | 82 | } else if (c < 0xc0 || c >= 0xfe) { |
H. Peter Anvin | 518df30 | 2008-06-14 16:53:48 -0700 | [diff] [blame] | 83 | /* Invalid UTF-8 */ |
| 84 | return -1; |
| 85 | } else if (c < 0xe0) { |
| 86 | v = c & 0x1f; |
| 87 | expect = 1; |
| 88 | vmin = 0x80; |
| 89 | } else if (c < 0xf0) { |
| 90 | v = c & 0x0f; |
| 91 | expect = 2; |
| 92 | vmin = 0x800; |
| 93 | } else if (c < 0xf8) { |
| 94 | v = c & 0x07; |
| 95 | expect = 3; |
| 96 | vmin = 0x10000; |
| 97 | } else if (c < 0xfc) { |
| 98 | v = c & 0x03; |
| 99 | expect = 4; |
| 100 | vmin = 0x200000; |
| 101 | } else { |
| 102 | v = c & 0x01; |
| 103 | expect = 5; |
| 104 | vmin = 0x4000000; |
| 105 | } |
| 106 | } |
| 107 | |
| 108 | return expect ? (size_t)-1 : outlen << 1; |
| 109 | |
| 110 | #undef EMIT |
| 111 | } |
| 112 | |
| 113 | /* |
| 114 | * Convert a string in UTF-8 format to UTF-32LE |
| 115 | */ |
| 116 | static size_t utf8_to_32le(uint8_t *str, size_t len, char *op) |
| 117 | { |
| 118 | #define EMIT(x) do { if (op) { WRITELONG(op,x); } outlen++; } while(0) |
| 119 | |
| 120 | size_t outlen = 0; |
| 121 | int expect = 0; |
| 122 | uint8_t c; |
| 123 | uint32_t v = 0, vmin = 0; |
| 124 | |
| 125 | while (len--) { |
| 126 | c = *str++; |
| 127 | |
| 128 | if (expect) { |
| 129 | if ((c & 0xc0) != 0x80) { |
| 130 | return -1; |
| 131 | } else { |
| 132 | v = (v << 6) | (c & 0x3f); |
| 133 | if (!--expect) { |
| 134 | if (v < vmin || (v >= 0xd800 && v <= 0xdfff)) { |
| 135 | return -1; |
| 136 | } else { |
| 137 | EMIT(v); |
| 138 | } |
| 139 | } |
| 140 | continue; |
| 141 | } |
| 142 | } |
| 143 | |
| 144 | if (c < 0x80) { |
| 145 | EMIT(c); |
H. Peter Anvin | 503e71d | 2008-06-14 21:07:09 -0700 | [diff] [blame] | 146 | } else if (c < 0xc0 || c >= 0xfe) { |
H. Peter Anvin | 518df30 | 2008-06-14 16:53:48 -0700 | [diff] [blame] | 147 | /* Invalid UTF-8 */ |
| 148 | return -1; |
| 149 | } else if (c < 0xe0) { |
| 150 | v = c & 0x1f; |
| 151 | expect = 1; |
| 152 | vmin = 0x80; |
| 153 | } else if (c < 0xf0) { |
| 154 | v = c & 0x0f; |
| 155 | expect = 2; |
| 156 | vmin = 0x800; |
| 157 | } else if (c < 0xf8) { |
| 158 | v = c & 0x07; |
| 159 | expect = 3; |
| 160 | vmin = 0x10000; |
| 161 | } else if (c < 0xfc) { |
| 162 | v = c & 0x03; |
| 163 | expect = 4; |
| 164 | vmin = 0x200000; |
| 165 | } else { |
| 166 | v = c & 0x01; |
| 167 | expect = 5; |
| 168 | vmin = 0x4000000; |
| 169 | } |
| 170 | } |
| 171 | |
| 172 | return expect ? (size_t)-1 : outlen << 2; |
| 173 | |
| 174 | #undef EMIT |
| 175 | } |
| 176 | |
| 177 | typedef size_t (*transform_func)(uint8_t *, size_t, char *); |
| 178 | |
| 179 | /* |
| 180 | * Apply a specific string transform and return it in a nasm_malloc'd |
| 181 | * buffer, returning the length. On error, returns (size_t)-1 and no |
| 182 | * buffer is allocated. |
| 183 | */ |
| 184 | size_t string_transform(char *str, size_t len, char **out, enum strfunc func) |
| 185 | { |
| 186 | /* This should match enum strfunc in nasm.h */ |
| 187 | static const transform_func str_transforms[] = { |
| 188 | utf8_to_16le, |
| 189 | utf8_to_32le, |
| 190 | }; |
| 191 | transform_func transform = str_transforms[func]; |
| 192 | size_t outlen; |
| 193 | uint8_t *s = (uint8_t *)str; |
H. Peter Anvin | 2cb033e | 2008-06-14 20:53:45 -0700 | [diff] [blame] | 194 | char *buf; |
H. Peter Anvin | 518df30 | 2008-06-14 16:53:48 -0700 | [diff] [blame] | 195 | |
| 196 | outlen = transform(s, len, NULL); |
| 197 | if (outlen == (size_t)-1) |
| 198 | return -1; |
| 199 | |
H. Peter Anvin | 2cb033e | 2008-06-14 20:53:45 -0700 | [diff] [blame] | 200 | *out = buf = nasm_malloc(outlen+1); |
| 201 | buf[outlen] = '\0'; /* Forcibly null-terminate the buffer */ |
| 202 | return transform(s, len, buf); |
H. Peter Anvin | 518df30 | 2008-06-14 16:53:48 -0700 | [diff] [blame] | 203 | } |