Haibo Huang | ee759ce | 2021-01-05 21:34:29 -0800 | [diff] [blame] | 1 | /* -*- Mode: c; tab-width: 8; indent-tabs-mode: 1; c-basic-offset: 8; -*- */ |
| 2 | /* |
| 3 | * Copyright (c) 1993, 1994, 1995, 1996, 1997 |
| 4 | * The Regents of the University of California. All rights reserved. |
| 5 | * |
| 6 | * Redistribution and use in source and binary forms, with or without |
| 7 | * modification, are permitted provided that the following conditions |
| 8 | * are met: |
| 9 | * 1. Redistributions of source code must retain the above copyright |
| 10 | * notice, this list of conditions and the following disclaimer. |
| 11 | * 2. 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 | * 3. All advertising materials mentioning features or use of this software |
| 15 | * must display the following acknowledgement: |
| 16 | * This product includes software developed by the Computer Systems |
| 17 | * Engineering Group at Lawrence Berkeley Laboratory. |
| 18 | * 4. Neither the name of the University nor of the Laboratory may be used |
| 19 | * to endorse or promote products derived from this software without |
| 20 | * specific prior written permission. |
| 21 | * |
| 22 | * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND |
| 23 | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 24 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
| 25 | * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE |
| 26 | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
| 27 | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
| 28 | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
| 29 | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
| 30 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
| 31 | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
| 32 | * SUCH DAMAGE. |
| 33 | */ |
| 34 | |
| 35 | #ifdef _WIN32 |
| 36 | #include <stdio.h> |
| 37 | |
| 38 | #include <pcap/pcap.h> /* Needed for PCAP_ERRBUF_SIZE */ |
| 39 | |
| 40 | #include "charconv.h" |
| 41 | |
| 42 | wchar_t * |
| 43 | cp_to_utf_16le(UINT codepage, const char *cp_string, DWORD flags) |
| 44 | { |
| 45 | int utf16le_len; |
| 46 | wchar_t *utf16le_string; |
| 47 | |
| 48 | /* |
| 49 | * Map from the specified code page to UTF-16LE. |
| 50 | * First, find out how big a buffer we'll need. |
| 51 | */ |
| 52 | utf16le_len = MultiByteToWideChar(codepage, flags, cp_string, -1, |
| 53 | NULL, 0); |
| 54 | if (utf16le_len == 0) { |
| 55 | /* |
| 56 | * Error. Fail with EINVAL. |
| 57 | */ |
| 58 | errno = EINVAL; |
| 59 | return (NULL); |
| 60 | } |
| 61 | |
| 62 | /* |
| 63 | * Now attempt to allocate a buffer for that. |
| 64 | */ |
| 65 | utf16le_string = malloc(utf16le_len * sizeof (wchar_t)); |
| 66 | if (utf16le_string == NULL) { |
| 67 | /* |
| 68 | * Not enough memory; assume errno has been |
| 69 | * set, and fail. |
| 70 | */ |
| 71 | return (NULL); |
| 72 | } |
| 73 | |
| 74 | /* |
| 75 | * Now convert. |
| 76 | */ |
| 77 | utf16le_len = MultiByteToWideChar(codepage, flags, cp_string, -1, |
| 78 | utf16le_string, utf16le_len); |
| 79 | if (utf16le_len == 0) { |
| 80 | /* |
| 81 | * Error. Fail with EINVAL. |
| 82 | * XXX - should this ever happen, given that |
| 83 | * we already ran the string through |
| 84 | * MultiByteToWideChar() to find out how big |
| 85 | * a buffer we needed? |
| 86 | */ |
| 87 | free(utf16le_string); |
| 88 | errno = EINVAL; |
| 89 | return (NULL); |
| 90 | } |
| 91 | return (utf16le_string); |
| 92 | } |
| 93 | |
| 94 | char * |
| 95 | utf_16le_to_cp(UINT codepage, const wchar_t *utf16le_string) |
| 96 | { |
| 97 | int cp_len; |
| 98 | char *cp_string; |
| 99 | |
| 100 | /* |
| 101 | * Map from UTF-16LE to the specified code page. |
| 102 | * First, find out how big a buffer we'll need. |
| 103 | * We convert composite characters to precomposed characters, |
| 104 | * as that's what Windows expects. |
| 105 | */ |
| 106 | cp_len = WideCharToMultiByte(codepage, WC_COMPOSITECHECK, |
| 107 | utf16le_string, -1, NULL, 0, NULL, NULL); |
| 108 | if (cp_len == 0) { |
| 109 | /* |
| 110 | * Error. Fail with EINVAL. |
| 111 | */ |
| 112 | errno = EINVAL; |
| 113 | return (NULL); |
| 114 | } |
| 115 | |
| 116 | /* |
| 117 | * Now attempt to allocate a buffer for that. |
| 118 | */ |
| 119 | cp_string = malloc(cp_len * sizeof (char)); |
| 120 | if (cp_string == NULL) { |
| 121 | /* |
| 122 | * Not enough memory; assume errno has been |
| 123 | * set, and fail. |
| 124 | */ |
| 125 | return (NULL); |
| 126 | } |
| 127 | |
| 128 | /* |
| 129 | * Now convert. |
| 130 | */ |
| 131 | cp_len = WideCharToMultiByte(codepage, WC_COMPOSITECHECK, |
| 132 | utf16le_string, -1, cp_string, cp_len, NULL, NULL); |
| 133 | if (cp_len == 0) { |
| 134 | /* |
| 135 | * Error. Fail with EINVAL. |
| 136 | * XXX - should this ever happen, given that |
| 137 | * we already ran the string through |
| 138 | * WideCharToMultiByte() to find out how big |
| 139 | * a buffer we needed? |
| 140 | */ |
| 141 | free(cp_string); |
| 142 | errno = EINVAL; |
| 143 | return (NULL); |
| 144 | } |
| 145 | return (cp_string); |
| 146 | } |
| 147 | |
| 148 | /* |
| 149 | * Convert an error message string from UTF-8 to the local code page, as |
| 150 | * best we can. |
| 151 | * |
| 152 | * The buffer is assumed to be PCAP_ERRBUF_SIZE bytes long; we truncate |
| 153 | * if it doesn't fit. |
| 154 | */ |
| 155 | void |
| 156 | utf_8_to_acp_truncated(char *errbuf) |
| 157 | { |
| 158 | wchar_t *utf_16_errbuf; |
| 159 | int retval; |
| 160 | DWORD err; |
| 161 | |
| 162 | /* |
| 163 | * Do this by converting to UTF-16LE and then to the local |
| 164 | * code page. That means we get to use Microsoft's |
| 165 | * conversion routines, rather than having to understand |
| 166 | * all the code pages ourselves, *and* that this routine |
| 167 | * can convert in place. |
| 168 | */ |
| 169 | |
| 170 | /* |
| 171 | * Map from UTF-8 to UTF-16LE. |
| 172 | * First, find out how big a buffer we'll need. |
| 173 | * Convert any invalid characters to REPLACEMENT CHARACTER. |
| 174 | */ |
| 175 | utf_16_errbuf = cp_to_utf_16le(CP_UTF8, errbuf, 0); |
| 176 | if (utf_16_errbuf == NULL) { |
| 177 | /* |
| 178 | * Error. Give up. |
| 179 | */ |
| 180 | snprintf(errbuf, PCAP_ERRBUF_SIZE, |
| 181 | "Can't convert error string to the local code page"); |
| 182 | return; |
| 183 | } |
| 184 | |
| 185 | /* |
| 186 | * Now, convert that to the local code page. |
| 187 | * Use the current thread's code page. For unconvertable |
| 188 | * characters, let it pick the "best fit" character. |
| 189 | * |
| 190 | * XXX - we'd like some way to do what utf_16le_to_utf_8_truncated() |
| 191 | * does if the buffer isn't big enough, but we don't want to have |
| 192 | * to handle all local code pages ourselves; doing so requires |
| 193 | * knowledge of all those code pages, including knowledge of how |
| 194 | * characters are formed in thoe code pages so that we can avoid |
| 195 | * cutting a multi-byte character into pieces. |
| 196 | * |
| 197 | * Converting to an un-truncated string using Windows APIs, and |
| 198 | * then copying to the buffer, still requires knowledge of how |
| 199 | * characters are formed in the target code page. |
| 200 | */ |
| 201 | retval = WideCharToMultiByte(CP_THREAD_ACP, 0, utf_16_errbuf, -1, |
| 202 | errbuf, PCAP_ERRBUF_SIZE, NULL, NULL); |
| 203 | if (retval == 0) { |
| 204 | err = GetLastError(); |
| 205 | free(utf_16_errbuf); |
| 206 | if (err == ERROR_INSUFFICIENT_BUFFER) |
| 207 | snprintf(errbuf, PCAP_ERRBUF_SIZE, |
| 208 | "The error string, in the local code page, didn't fit in the buffer"); |
| 209 | else |
| 210 | snprintf(errbuf, PCAP_ERRBUF_SIZE, |
| 211 | "Can't convert error string to the local code page"); |
| 212 | return; |
| 213 | } |
| 214 | free(utf_16_errbuf); |
| 215 | } |
| 216 | #endif |