| 1 | /* |
| 2 | * This file is part of DisOrder. |
| 3 | * Copyright (C) 2004, 2005, 2007, 2008, 2013 Richard Kettlewell |
| 4 | * |
| 5 | * This program is free software: you can redistribute it and/or modify |
| 6 | * it under the terms of the GNU General Public License as published by |
| 7 | * the Free Software Foundation, either version 3 of the License, or |
| 8 | * (at your option) any later version. |
| 9 | * |
| 10 | * This program is distributed in the hope that it will be useful, |
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | * GNU General Public License for more details. |
| 14 | * |
| 15 | * You should have received a copy of the GNU General Public License |
| 16 | * along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 17 | */ |
| 18 | /** @file lib/charset.c @brief Character set conversion */ |
| 19 | |
| 20 | #include "common.h" |
| 21 | |
| 22 | #if HAVE_ICONV_H |
| 23 | # include <iconv.h> |
| 24 | #endif |
| 25 | #include <errno.h> |
| 26 | #if HAVE_LANGINFO_H |
| 27 | # include <langinfo.h> |
| 28 | #endif |
| 29 | |
| 30 | #include "mem.h" |
| 31 | #include "log.h" |
| 32 | #include "charset.h" |
| 33 | #include "configuration.h" |
| 34 | #include "vector.h" |
| 35 | #include "unicode.h" |
| 36 | |
| 37 | #if _WIN32 |
| 38 | // TODO WIN32 we assume UTF-8 here, which is *definitely wrong* |
| 39 | char *mb2utf8(const char *mb) { |
| 40 | return xstrdup(mb); |
| 41 | } |
| 42 | |
| 43 | char *utf82mb(const char *utf8) { |
| 44 | return xstrdup(utf8); |
| 45 | } |
| 46 | #else |
| 47 | |
| 48 | /** @brief Low-level converstion routine |
| 49 | * @param from Source encoding |
| 50 | * @param to Destination encoding |
| 51 | * @param ptr First byte to convert |
| 52 | * @param n Number of bytes to convert |
| 53 | * @return Converted text, 0-terminated; or NULL on error. |
| 54 | */ |
| 55 | static void *convert(const char *from, const char *to, |
| 56 | const void *ptr, size_t n) { |
| 57 | iconv_t i; |
| 58 | size_t len; |
| 59 | char *buf = 0, *s, *d; |
| 60 | size_t bufsize = 0, sl, dl; |
| 61 | |
| 62 | if((i = iconv_open(to, from)) == (iconv_t)-1) |
| 63 | disorder_fatal(errno, "error calling iconv_open"); |
| 64 | do { |
| 65 | bufsize = bufsize ? 2 * bufsize : 32; |
| 66 | buf = xrealloc_noptr(buf, bufsize); |
| 67 | iconv(i, 0, 0, 0, 0); |
| 68 | s = (char *)ptr; |
| 69 | sl = n; |
| 70 | d = buf; |
| 71 | dl = bufsize; |
| 72 | /* (void *) to work around FreeBSD's nonstandard iconv prototype */ |
| 73 | len = iconv(i, (void *)&s, &sl, &d, &dl); |
| 74 | } while(len == (size_t)-1 && errno == E2BIG); |
| 75 | iconv_close(i); |
| 76 | if(len == (size_t)-1) { |
| 77 | disorder_error(errno, "error converting from %s to %s", from, to); |
| 78 | return 0; |
| 79 | } |
| 80 | return buf; |
| 81 | } |
| 82 | |
| 83 | /** @brief Convert from the local multibyte encoding to UTF-8 |
| 84 | * @param mb String in current locale's multibyte encoding |
| 85 | * @return Same string in UTF-8 |
| 86 | */ |
| 87 | char *mb2utf8(const char *mb) { |
| 88 | return convert(nl_langinfo(CODESET), "UTF-8", mb, strlen(mb) + 1); |
| 89 | } |
| 90 | |
| 91 | /** @brief Convert from UTF-8 to the local multibyte encoding |
| 92 | * @param utf8 String in UTF-8 |
| 93 | * @return Same string in current locale's multibyte encoding |
| 94 | */ |
| 95 | char *utf82mb(const char *utf8) { |
| 96 | return convert("UTF-8", nl_langinfo(CODESET), utf8, strlen(utf8) + 1); |
| 97 | } |
| 98 | |
| 99 | /** @brief Convert from encoding @p from to UTF-8 |
| 100 | * @param from Source encoding |
| 101 | * @param any String in encoding @p from |
| 102 | * @return @p any converted to UTF-8 |
| 103 | */ |
| 104 | char *any2utf8(const char *from, const char *any) { |
| 105 | return convert(from, "UTF-8", any, strlen(any) + 1); |
| 106 | } |
| 107 | |
| 108 | /** @brief Convert from encoding @p from to the local multibyte encoding |
| 109 | * @param from Source encoding |
| 110 | * @param any String in encoding @p from |
| 111 | * @return @p any converted to current locale's multibyte encoding |
| 112 | */ |
| 113 | char *any2mb(const char *from, const char *any) { |
| 114 | if(from) return convert(from, nl_langinfo(CODESET), any, strlen(any) + 1); |
| 115 | else return xstrdup(any); |
| 116 | } |
| 117 | |
| 118 | /** @brief Convert from encoding @p from to encoding @p to |
| 119 | * @param from Source encoding |
| 120 | * @param to Destination encoding |
| 121 | * @param any String in encoding @p from |
| 122 | * @return @p any converted to encoding @p to |
| 123 | */ |
| 124 | char *any2any(const char *from, |
| 125 | const char *to, |
| 126 | const char *any) { |
| 127 | if(from || to) return convert(from, to, any, strlen(any) + 1); |
| 128 | else return xstrdup(any); |
| 129 | } |
| 130 | |
| 131 | #endif |
| 132 | |
| 133 | /** @brief Truncate a string for display purposes |
| 134 | * @param s Pointer to UTF-8 string |
| 135 | * @param max Maximum number of columns |
| 136 | * @return @p or truncated string (never NULL) |
| 137 | * |
| 138 | * Returns a string that is no longer than @p max graphemes long and is either |
| 139 | * (canonically) equal to @p s or is a truncated form of it with an ellipsis |
| 140 | * appended. |
| 141 | * |
| 142 | * We don't take display width into account (tricky for HTML!) and we don't |
| 143 | * attempt to implement the Bidi algorithm. If you have track names for which |
| 144 | * either of these matter in practice then get in touch. |
| 145 | */ |
| 146 | const char *truncate_for_display(const char *s, long max) { |
| 147 | uint32_t *s32; |
| 148 | size_t l32, cut; |
| 149 | utf32_iterator it; |
| 150 | long graphemes; |
| 151 | |
| 152 | /* Convert to UTF-32 for processing */ |
| 153 | if(!(s32 = utf8_to_utf32(s, strlen(s), &l32))) |
| 154 | return 0; |
| 155 | it = utf32_iterator_new(s32, l32); |
| 156 | cut = l32; |
| 157 | graphemes = 0; /* # of graphemes left of it */ |
| 158 | while(graphemes <= max && utf32_iterator_where(it) < l32) { |
| 159 | if(graphemes == max - 1) |
| 160 | cut = utf32_iterator_where(it); |
| 161 | utf32_iterator_advance(it, 1); |
| 162 | if(utf32_iterator_grapheme_boundary(it)) |
| 163 | ++graphemes; |
| 164 | } |
| 165 | if(graphemes > max) { /* we need to cut */ |
| 166 | s32[cut] = 0x2026; /* HORIZONTAL ELLIPSIS */ |
| 167 | l32 = cut + 1; |
| 168 | s = utf32_to_utf8(s32, l32, 0); |
| 169 | } |
| 170 | xfree(s32); |
| 171 | return s; |
| 172 | } |
| 173 | |
| 174 | /* |
| 175 | Local Variables: |
| 176 | c-basic-offset:2 |
| 177 | comment-column:40 |
| 178 | fill-column:79 |
| 179 | indent-tabs-mode:nil |
| 180 | End: |
| 181 | */ |