| 1 | /* |
| 2 | * Copyright (C) 2001 Peter Harris <peter.harris@hummingbird.com> |
| 3 | * Copyright (C) 2001 Edmund Grimley Evans <edmundo@rano.org> |
| 4 | * |
| 5 | * Buffer overflow checking added: Josh Coalson, 9/9/2007 |
| 6 | * |
| 7 | * Win32 part rewritten: lvqcl, 2/2/2016 |
| 8 | * |
| 9 | * This program is free software; you can redistribute it and/or modify |
| 10 | * it under the terms of the GNU General Public License as published by |
| 11 | * the Free Software Foundation; either version 2 of the License, or |
| 12 | * (at your option) any later version. |
| 13 | * |
| 14 | * This program is distributed in the hope that it will be useful, |
| 15 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 16 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 17 | * GNU General Public License for more details. |
| 18 | * |
| 19 | * You should have received a copy of the GNU General Public License along |
| 20 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 21 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. |
| 22 | */ |
| 23 | |
| 24 | /* |
| 25 | * Convert a string between UTF-8 and the locale's charset. |
| 26 | */ |
| 27 | |
| 28 | #ifdef HAVE_CONFIG_H |
| 29 | # include <config.h> |
| 30 | #endif |
| 31 | |
| 32 | #include <stdlib.h> |
| 33 | |
| 34 | #include "share/alloc.h" |
| 35 | #include "share/utf8.h" |
| 36 | |
| 37 | #ifdef _WIN32 |
| 38 | |
| 39 | #include <windows.h> |
| 40 | |
| 41 | int utf8_encode(const char *from, char **to) |
| 42 | { |
| 43 | wchar_t *unicode = NULL; |
| 44 | char *utf8 = NULL; |
| 45 | int ret = -1; |
| 46 | |
| 47 | do { |
| 48 | int len; |
| 49 | |
| 50 | len = MultiByteToWideChar(CP_ACP, MB_PRECOMPOSED, from, -1, NULL, 0); |
| 51 | if(len == 0) break; |
| 52 | |
| 53 | unicode = (wchar_t*) safe_malloc_mul_2op_((size_t)len, sizeof(wchar_t)); |
| 54 | if(unicode == NULL) break; |
| 55 | |
| 56 | len = MultiByteToWideChar(CP_ACP, MB_PRECOMPOSED, from, -1, unicode, len); |
| 57 | if(len == 0) break; |
| 58 | |
| 59 | len = WideCharToMultiByte(CP_UTF8, 0, unicode, -1, NULL, 0, NULL, NULL); |
| 60 | if(len == 0) break; |
| 61 | |
| 62 | utf8 = (char*) safe_malloc_mul_2op_((size_t)len, sizeof(char)); |
| 63 | if(utf8 == NULL) break; |
| 64 | |
| 65 | len = WideCharToMultiByte(CP_UTF8, 0, unicode, -1, utf8, len, NULL, NULL); |
| 66 | if(len == 0) break; |
| 67 | |
| 68 | ret = 0; |
| 69 | |
| 70 | } while(0); |
| 71 | |
| 72 | free(unicode); |
| 73 | |
| 74 | if(ret == 0) { |
| 75 | *to = utf8; |
| 76 | } else { |
| 77 | free(utf8); |
| 78 | *to = NULL; |
| 79 | } |
| 80 | |
| 81 | return ret; |
| 82 | } |
| 83 | |
| 84 | int utf8_decode(const char *from, char **to) |
| 85 | { |
| 86 | wchar_t *unicode = NULL; |
| 87 | char *acp = NULL; |
| 88 | int ret = -1; |
| 89 | |
| 90 | do { |
| 91 | int len; |
| 92 | |
| 93 | len = MultiByteToWideChar(CP_UTF8, 0, from, -1, NULL, 0); |
| 94 | if(len == 0) break; |
| 95 | |
| 96 | unicode = (wchar_t*) safe_malloc_mul_2op_((size_t)len, sizeof(wchar_t)); |
| 97 | if(unicode == NULL) break; |
| 98 | |
| 99 | len = MultiByteToWideChar(CP_UTF8, 0, from, -1, unicode, len); |
| 100 | if(len == 0) break; |
| 101 | |
| 102 | len = WideCharToMultiByte(CP_ACP, WC_COMPOSITECHECK, unicode, -1, NULL, 0, NULL, NULL); |
| 103 | if(len == 0) break; |
| 104 | |
| 105 | acp = (char*) safe_malloc_mul_2op_((size_t)len, sizeof(char)); |
| 106 | if(acp == NULL) break; |
| 107 | |
| 108 | len = WideCharToMultiByte(CP_ACP, WC_COMPOSITECHECK, unicode, -1, acp, len, NULL, NULL); |
| 109 | if(len == 0) break; |
| 110 | |
| 111 | ret = 0; |
| 112 | |
| 113 | } while(0); |
| 114 | |
| 115 | free(unicode); |
| 116 | |
| 117 | if(ret == 0) { |
| 118 | *to = acp; |
| 119 | } else { |
| 120 | free(acp); |
| 121 | *to = NULL; |
| 122 | } |
| 123 | |
| 124 | return ret; |
| 125 | } |
| 126 | |
| 127 | #else /* End win32. Rest is for real operating systems */ |
| 128 | |
| 129 | |
| 130 | #ifdef HAVE_LANGINFO_CODESET |
| 131 | #include <langinfo.h> |
| 132 | #endif |
| 133 | |
| 134 | #include <string.h> |
| 135 | |
| 136 | #include "share/safe_str.h" |
| 137 | #include "iconvert.h" |
| 138 | #include "charset.h" |
| 139 | |
| 140 | static const char *current_charset(void) |
| 141 | { |
| 142 | const char *c = 0; |
| 143 | #ifdef HAVE_LANGINFO_CODESET |
| 144 | c = nl_langinfo(CODESET); |
| 145 | #endif |
| 146 | |
| 147 | if (!c) |
| 148 | c = getenv("CHARSET"); |
| 149 | |
| 150 | return c? c : "US-ASCII"; |
| 151 | } |
| 152 | |
| 153 | static int convert_buffer(const char *fromcode, const char *tocode, |
| 154 | const char *from, size_t fromlen, |
| 155 | char **to, size_t *tolen) |
| 156 | { |
| 157 | int ret = -1; |
| 158 | |
| 159 | #ifdef HAVE_ICONV |
| 160 | ret = iconvert(fromcode, tocode, from, fromlen, to, tolen); |
| 161 | if (ret != -1) |
| 162 | return ret; |
| 163 | #endif |
| 164 | |
| 165 | #ifndef HAVE_ICONV /* should be ifdef USE_CHARSET_CONVERT */ |
| 166 | ret = charset_convert(fromcode, tocode, from, fromlen, to, tolen); |
| 167 | if (ret != -1) |
| 168 | return ret; |
| 169 | #endif |
| 170 | |
| 171 | return ret; |
| 172 | } |
| 173 | |
| 174 | static int convert_string(const char *fromcode, const char *tocode, |
| 175 | const char *from, char **to, char replace) |
| 176 | { |
| 177 | int ret; |
| 178 | size_t fromlen; |
| 179 | char *s; |
| 180 | |
| 181 | fromlen = strlen(from); |
| 182 | ret = convert_buffer(fromcode, tocode, from, fromlen, to, 0); |
| 183 | if (ret == -2) |
| 184 | return -1; |
| 185 | if (ret != -1) |
| 186 | return ret; |
| 187 | |
| 188 | s = safe_malloc_add_2op_(fromlen, /*+*/1); |
| 189 | if (!s) |
| 190 | return -1; |
| 191 | safe_strncpy(s, from, fromlen + 1); |
| 192 | *to = s; |
| 193 | for (; *s; s++) |
| 194 | if (*s & ~0x7f) |
| 195 | *s = replace; |
| 196 | return 3; |
| 197 | } |
| 198 | |
| 199 | int utf8_encode(const char *from, char **to) |
| 200 | { |
| 201 | return convert_string(current_charset(), "UTF-8", from, to, '#'); |
| 202 | } |
| 203 | |
| 204 | int utf8_decode(const char *from, char **to) |
| 205 | { |
| 206 | return convert_string("UTF-8", current_charset(), from, to, '?'); |
| 207 | } |
| 208 | |
| 209 | #endif |