lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame^] | 1 | /* Conversion module for Unicode |
| 2 | Copyright (C) 1999-2015 Free Software Foundation, Inc. |
| 3 | This file is part of the GNU C Library. |
| 4 | Contributed by Ulrich Drepper <drepper@cygnus.com>, 1999. |
| 5 | |
| 6 | The GNU C Library is free software; you can redistribute it and/or |
| 7 | modify it under the terms of the GNU Lesser General Public |
| 8 | License as published by the Free Software Foundation; either |
| 9 | version 2.1 of the License, or (at your option) any later version. |
| 10 | |
| 11 | The GNU C Library is distributed in the hope that it will be useful, |
| 12 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 13 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 14 | Lesser General Public License for more details. |
| 15 | |
| 16 | You should have received a copy of the GNU Lesser General Public |
| 17 | License along with the GNU C Library; if not, see |
| 18 | <http://www.gnu.org/licenses/>. */ |
| 19 | |
| 20 | #include <byteswap.h> |
| 21 | #include <dlfcn.h> |
| 22 | #include <gconv.h> |
| 23 | #include <stddef.h> |
| 24 | #include <stdint.h> |
| 25 | #include <stdlib.h> |
| 26 | #include <string.h> |
| 27 | |
| 28 | /* This is the Byte Order Mark character (BOM). */ |
| 29 | #define BOM 0xfeff |
| 30 | /* And in the other endian format. */ |
| 31 | #define BOM_OE 0xfffe |
| 32 | |
| 33 | |
| 34 | /* Definitions used in the body of the `gconv' function. */ |
| 35 | #define FROM_LOOP from_unicode_loop |
| 36 | #define TO_LOOP to_unicode_loop |
| 37 | #define DEFINE_INIT 0 |
| 38 | #define DEFINE_FINI 0 |
| 39 | #define MIN_NEEDED_FROM 2 |
| 40 | #define MIN_NEEDED_TO 4 |
| 41 | #define ONE_DIRECTION 0 |
| 42 | #define FROM_DIRECTION (dir == from_unicode) |
| 43 | #define PREPARE_LOOP \ |
| 44 | enum direction dir = ((struct unicode_data *) step->__data)->dir; \ |
| 45 | int swap; \ |
| 46 | if (FROM_DIRECTION) \ |
| 47 | { \ |
| 48 | if (data->__invocation_counter == 0) \ |
| 49 | { \ |
| 50 | /* We have to find out which byte order the file is encoded in. */ \ |
| 51 | if (inptr + 2 > inend) \ |
| 52 | return (inptr == inend \ |
| 53 | ? __GCONV_EMPTY_INPUT : __GCONV_INCOMPLETE_INPUT); \ |
| 54 | \ |
| 55 | if (get16u (inptr) == BOM) \ |
| 56 | /* Simply ignore the BOM character. */ \ |
| 57 | *inptrp = inptr += 2; \ |
| 58 | else if (get16u (inptr) == BOM_OE) \ |
| 59 | { \ |
| 60 | data->__flags |= __GCONV_SWAP; \ |
| 61 | *inptrp = inptr += 2; \ |
| 62 | } \ |
| 63 | } \ |
| 64 | } \ |
| 65 | else if (!data->__internal_use && data->__invocation_counter == 0) \ |
| 66 | { \ |
| 67 | /* Emit the Byte Order Mark. */ \ |
| 68 | if (__glibc_unlikely (outbuf + 2 > outend)) \ |
| 69 | return __GCONV_FULL_OUTPUT; \ |
| 70 | \ |
| 71 | put16u (outbuf, BOM); \ |
| 72 | outbuf += 2; \ |
| 73 | } \ |
| 74 | swap = data->__flags & __GCONV_SWAP; |
| 75 | #define EXTRA_LOOP_ARGS , swap |
| 76 | |
| 77 | |
| 78 | /* Direction of the transformation. */ |
| 79 | enum direction |
| 80 | { |
| 81 | illegal_dir, |
| 82 | to_unicode, |
| 83 | from_unicode |
| 84 | }; |
| 85 | |
| 86 | struct unicode_data |
| 87 | { |
| 88 | enum direction dir; |
| 89 | }; |
| 90 | |
| 91 | |
| 92 | extern int gconv_init (struct __gconv_step *step); |
| 93 | int |
| 94 | gconv_init (struct __gconv_step *step) |
| 95 | { |
| 96 | /* Determine which direction. */ |
| 97 | struct unicode_data *new_data; |
| 98 | enum direction dir = illegal_dir; |
| 99 | int result; |
| 100 | |
| 101 | if (strcmp (step->__from_name, "UNICODE//") == 0) |
| 102 | dir = from_unicode; |
| 103 | else |
| 104 | dir = to_unicode; |
| 105 | |
| 106 | new_data = (struct unicode_data *) malloc (sizeof (struct unicode_data)); |
| 107 | |
| 108 | result = __GCONV_NOMEM; |
| 109 | if (new_data != NULL) |
| 110 | { |
| 111 | new_data->dir = dir; |
| 112 | step->__data = new_data; |
| 113 | |
| 114 | if (dir == from_unicode) |
| 115 | { |
| 116 | step->__min_needed_from = MIN_NEEDED_FROM; |
| 117 | step->__max_needed_from = MIN_NEEDED_FROM; |
| 118 | step->__min_needed_to = MIN_NEEDED_TO; |
| 119 | step->__max_needed_to = MIN_NEEDED_TO; |
| 120 | } |
| 121 | else |
| 122 | { |
| 123 | step->__min_needed_from = MIN_NEEDED_TO; |
| 124 | step->__max_needed_from = MIN_NEEDED_TO; |
| 125 | step->__min_needed_to = MIN_NEEDED_FROM; |
| 126 | step->__max_needed_to = MIN_NEEDED_FROM; |
| 127 | } |
| 128 | |
| 129 | step->__stateful = 0; |
| 130 | |
| 131 | result = __GCONV_OK; |
| 132 | } |
| 133 | |
| 134 | return result; |
| 135 | } |
| 136 | |
| 137 | |
| 138 | extern void gconv_end (struct __gconv_step *data); |
| 139 | void |
| 140 | gconv_end (struct __gconv_step *data) |
| 141 | { |
| 142 | free (data->__data); |
| 143 | } |
| 144 | |
| 145 | |
| 146 | /* Convert from the internal (UCS4-like) format to UCS2. */ |
| 147 | #define MIN_NEEDED_INPUT MIN_NEEDED_TO |
| 148 | #define MIN_NEEDED_OUTPUT MIN_NEEDED_FROM |
| 149 | #define LOOPFCT TO_LOOP |
| 150 | #define BODY \ |
| 151 | { \ |
| 152 | uint32_t c = get32 (inptr); \ |
| 153 | \ |
| 154 | if (__glibc_unlikely (c >= 0x10000)) \ |
| 155 | { \ |
| 156 | UNICODE_TAG_HANDLER (c, 4); \ |
| 157 | STANDARD_TO_LOOP_ERR_HANDLER (4); \ |
| 158 | } \ |
| 159 | else if (__glibc_unlikely (c >= 0xd800 && c < 0xe000)) \ |
| 160 | { \ |
| 161 | /* Surrogate characters in UCS-4 input are not valid. \ |
| 162 | We must catch this, because the UCS-2 output might be \ |
| 163 | interpreted as UTF-16 by other programs. If we let \ |
| 164 | surrogates pass through, attackers could make a security \ |
| 165 | hole exploit by synthesizing any desired plane 1-16 \ |
| 166 | character. */ \ |
| 167 | result = __GCONV_ILLEGAL_INPUT; \ |
| 168 | if (! ignore_errors_p ()) \ |
| 169 | break; \ |
| 170 | inptr += 4; \ |
| 171 | ++*irreversible; \ |
| 172 | continue; \ |
| 173 | } \ |
| 174 | else \ |
| 175 | { \ |
| 176 | put16 (outptr, c); \ |
| 177 | outptr += 2; \ |
| 178 | } \ |
| 179 | \ |
| 180 | inptr += 4; \ |
| 181 | } |
| 182 | #define LOOP_NEED_FLAGS |
| 183 | #define EXTRA_LOOP_DECLS \ |
| 184 | , int swap |
| 185 | #include <iconv/loop.c> |
| 186 | |
| 187 | |
| 188 | /* Convert from UCS2 to the internal (UCS4-like) format. */ |
| 189 | #define MIN_NEEDED_INPUT MIN_NEEDED_FROM |
| 190 | #define MIN_NEEDED_OUTPUT MIN_NEEDED_TO |
| 191 | #define LOOPFCT FROM_LOOP |
| 192 | #define BODY \ |
| 193 | { \ |
| 194 | uint16_t u1 = get16 (inptr); \ |
| 195 | \ |
| 196 | if (swap) \ |
| 197 | u1 = bswap_16 (u1); \ |
| 198 | \ |
| 199 | if (__glibc_unlikely (u1 >= 0xd800 && u1 < 0xe000)) \ |
| 200 | { \ |
| 201 | /* Surrogate characters in UCS-2 input are not valid. Reject \ |
| 202 | them. (Catching this here is not security relevant.) */ \ |
| 203 | STANDARD_FROM_LOOP_ERR_HANDLER (2); \ |
| 204 | } \ |
| 205 | \ |
| 206 | put32 (outptr, u1); \ |
| 207 | \ |
| 208 | inptr += 2; \ |
| 209 | outptr += 4; \ |
| 210 | } |
| 211 | #define LOOP_NEED_FLAGS |
| 212 | #define EXTRA_LOOP_DECLS \ |
| 213 | , int swap |
| 214 | #include <iconv/loop.c> |
| 215 | |
| 216 | |
| 217 | /* Now define the toplevel functions. */ |
| 218 | #include <iconv/skeleton.c> |