1 /*- 2 * SPDX-License-Identifier: BSD-2-Clause 3 * 4 * Copyright (c) 2003 Ryuichiro Imura 5 * All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted provided that the following conditions 9 * are met: 10 * 1. Redistributions of source code must retain the above copyright 11 * notice, this list of conditions and the following disclaimer. 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 15 * 16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 26 * SUCH DAMAGE. 27 * 28 * $FreeBSD$ 29 */ 30 31 /* 32 * kiconv(3) requires shared linked, and reduce module size 33 * when statically linked. 34 */ 35 36 #ifdef PIC 37 38 /* 39 * Why do we need quirks? 40 * Since each vendors has their own Unicode mapping rules, 41 * we need some quirks until iconv(3) supports them. 42 * We can define Microsoft mappings here. 43 * 44 * For example, the eucJP and Unocode mapping rule is based on 45 * the JIS standard. Since Microsoft uses cp932 for Unicode mapping 46 * which is not truly based on the JIS standard, reading a file 47 * system created by Microsoft Windows family using eucJP/Unicode 48 * mapping rule will cause a problem. That's why we define eucJP-ms here. 49 * The eucJP-ms has been defined by The Open Group Japan Vendor Council. 50 * 51 * Well, Apple Mac OS also has their own Unicode mappings, 52 * but we won't require these quirks here, because HFS doesn't have 53 * Unicode and HFS+ has decomposed Unicode which can not be 54 * handled by this xlat16 converter. 55 */ 56 57 #include <sys/types.h> 58 #include <sys/iconv.h> 59 60 #include <stdio.h> 61 #include <string.h> 62 63 #include "quirks.h" 64 65 /* 66 * All lists of quirk character set 67 */ 68 static struct { 69 int vendor; /* reserved for non MS mapping */ 70 const char *base_codeset, *quirk_codeset; 71 } quirk_list[] = { 72 { KICONV_VENDOR_MICSFT, "eucJP", "eucJP-ms" }, 73 { KICONV_VENDOR_MICSFT, "EUC-JP", "eucJP-ms" }, 74 { KICONV_VENDOR_MICSFT, "SJIS", "SJIS-ms" }, 75 { KICONV_VENDOR_MICSFT, "Shift_JIS", "SJIS-ms" }, 76 { KICONV_VENDOR_MICSFT, "Big5", "Big5-ms" } 77 }; 78 79 /* 80 * The character list to replace for Japanese MS-Windows. 81 */ 82 static struct quirk_replace_list quirk_jis_cp932[] = { 83 { 0x00a2, 0xffe0 }, /* Cent Sign, Fullwidth Cent Sign */ 84 { 0x00a3, 0xffe1 }, /* Pound Sign, Fullwidth Pound Sign */ 85 { 0x00ac, 0xffe2 }, /* Not Sign, Fullwidth Not Sign */ 86 { 0x2016, 0x2225 }, /* Double Vertical Line, Parallel To */ 87 { 0x203e, 0x007e }, /* Overline, Tilde */ 88 { 0x2212, 0xff0d }, /* Minus Sign, Fullwidth Hyphenminus */ 89 { 0x301c, 0xff5e } /* Wave Dash, Fullwidth Tilde */ 90 }; 91 92 /* 93 * All entries of quirks 94 */ 95 #define NumOf(n) (sizeof((n)) / sizeof((n)[0])) 96 static struct { 97 const char *quirk_codeset, *iconv_codeset, *pair_codeset; 98 struct quirk_replace_list (*replace_list)[]; 99 size_t num_of_replaces; 100 } quirk_table[] = { 101 { 102 "eucJP-ms", "eucJP", ENCODING_UNICODE, 103 (struct quirk_replace_list (*)[])&quirk_jis_cp932, 104 NumOf(quirk_jis_cp932) 105 }, 106 { 107 "SJIS-ms", "CP932", ENCODING_UNICODE, 108 /* XXX - quirk_replace_list should be NULL */ 109 (struct quirk_replace_list (*)[])&quirk_jis_cp932, 110 NumOf(quirk_jis_cp932) 111 }, 112 { 113 "Big5-ms", "CP950", ENCODING_UNICODE, 114 NULL, 0 115 } 116 }; 117 118 119 const char * 120 kiconv_quirkcs(const char* base, int vendor) 121 { 122 size_t i; 123 124 /* 125 * We should compare codeset names ignoring case here, 126 * so that quirk could be used for all of the user input 127 * patterns. 128 */ 129 for (i = 0; i < NumOf(quirk_list); i++) 130 if (quirk_list[i].vendor == vendor && 131 strcasecmp(quirk_list[i].base_codeset, base) == 0) 132 return (quirk_list[i].quirk_codeset); 133 134 return (base); 135 } 136 137 /* 138 * Internal Functions 139 */ 140 const char * 141 search_quirk(const char *given_codeset, 142 const char *pair_codeset, 143 struct quirk_replace_list **replace_list, 144 size_t *num_of_replaces) 145 { 146 size_t i; 147 148 *replace_list = NULL; 149 *num_of_replaces = 0; 150 for (i = 0; i < NumOf(quirk_table); i++) 151 if (strcmp(quirk_table[i].quirk_codeset, given_codeset) == 0) { 152 if (strcmp(quirk_table[i].pair_codeset, pair_codeset) == 0) { 153 *replace_list = *quirk_table[i].replace_list; 154 *num_of_replaces = quirk_table[i].num_of_replaces; 155 } 156 return (quirk_table[i].iconv_codeset); 157 } 158 159 return (given_codeset); 160 } 161 162 uint16_t 163 quirk_vendor2unix(uint16_t c, struct quirk_replace_list *replace_list, size_t num) 164 { 165 size_t i; 166 167 for (i = 0; i < num; i++) 168 if (replace_list[i].vendor_code == c) 169 return (replace_list[i].standard_code); 170 171 return (c); 172 } 173 174 uint16_t 175 quirk_unix2vendor(uint16_t c, struct quirk_replace_list *replace_list, size_t num) 176 { 177 size_t i; 178 179 for (i = 0; i < num; i++) 180 if (replace_list[i].standard_code == c) 181 return (replace_list[i].vendor_code); 182 183 return (c); 184 } 185 186 #else /* statically linked */ 187 188 #include <sys/types.h> 189 #include <sys/iconv.h> 190 191 const char * 192 kiconv_quirkcs(const char* base __unused, int vendor __unused) 193 { 194 195 return (base); 196 } 197 198 #endif /* PIC */ 199