src/plugin_xmms/charset.c

   1 /* libxmms-flac - XMMS FLAC input plugin
   2  * Copyright (C) 2002,2003,2004,2005,2006,2007,2008,2009  Daisuke Shimamura
   3  *
   4  * Almost from charset.c
   5  *  EasyTAG - Tag editor for MP3 and OGG files
   6  *  Copyright (C) 1999-2001  Håvard Kvålen <havardk@xmms.org>
   7  *
   8  * This program is free software; you can redistribute it and/or
   9  * modify it under the terms of the GNU General Public License
  10  * as published by the Free Software Foundation; either version 2
  11  * of the License, or (at your option) any later version.
  12  *
  13  * This program is distributed in the hope that it will be useful,
  14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16  * GNU General Public License for more details.
  17  *
  18  * You should have received a copy of the GNU General Public License along
  19  * with this program; if not, write to the Free Software Foundation, Inc.,
  20  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  21  */
  22
  23 #include "plugin.h"
  24
  25 #include <stdlib.h>
  26 #include <glib.h>
  27 #include <string.h>
  28 #include <errno.h>
  29
  30 #include "plugin_common/charset.h"
  31 #include "charset.h"
  32 #include "configure.h"
  33 #include "locale_hack.h"
  34
  35
  36 /****************
  37  * Declarations *
  38  ****************/
  39
  40 #define CHARSET_TRANS_ARRAY_LEN ( sizeof(charset_trans_array) / sizeof((charset_trans_array)[0]) )
  41 const CharsetInfo charset_trans_array[] = {
  42         {N_("Arabic (IBM-864)"),                  "IBM864"        },
  43         {N_("Arabic (ISO-8859-6)"),               "ISO-8859-6"    },
  44         {N_("Arabic (Windows-1256)"),             "windows-1256"  },
  45         {N_("Baltic (ISO-8859-13)"),              "ISO-8859-13"   },
  46         {N_("Baltic (ISO-8859-4)"),               "ISO-8859-4"    },
  47         {N_("Baltic (Windows-1257)"),             "windows-1257"  },
  48         {N_("Celtic (ISO-8859-14)"),              "ISO-8859-14"   },
  49         {N_("Central European (IBM-852)"),        "IBM852"        },
  50         {N_("Central European (ISO-8859-2)"),     "ISO-8859-2"    },
  51         {N_("Central European (Windows-1250)"),   "windows-1250"  },
  52         {N_("Chinese Simplified (GB18030)"),      "gb18030"       },
  53         {N_("Chinese Simplified (GB2312)"),       "GB2312"        },
  54         {N_("Chinese Traditional (Big5)"),        "Big5"          },
  55         {N_("Chinese Traditional (Big5-HKSCS)"),  "Big5-HKSCS"    },
  56         {N_("Cyrillic (IBM-855)"),                "IBM855"        },
  57         {N_("Cyrillic (ISO-8859-5)"),             "ISO-8859-5"    },
  58         {N_("Cyrillic (ISO-IR-111)"),             "ISO-IR-111"    },
  59         {N_("Cyrillic (KOI8-R)"),                 "KOI8-R"        },
  60         {N_("Cyrillic (Windows-1251)"),           "windows-1251"  },
  61         {N_("Cyrillic/Russian (CP-866)"),         "IBM866"        },
  62         {N_("Cyrillic/Ukrainian (KOI8-U)"),       "KOI8-U"        },
  63         {N_("English (US-ASCII)"),                "us-ascii"      },
  64         {N_("Greek (ISO-8859-7)"),                "ISO-8859-7"    },
  65         {N_("Greek (Windows-1253)"),              "windows-1253"  },
  66         {N_("Hebrew (IBM-862)"),                  "IBM862"        },
  67         {N_("Hebrew (Windows-1255)"),             "windows-1255"  },
  68         {N_("Japanese (EUC-JP)"),                 "EUC-JP"        },
  69         {N_("Japanese (ISO-2022-JP)"),            "ISO-2022-JP"   },
  70         {N_("Japanese (Shift_JIS)"),              "Shift_JIS"     },
  71         {N_("Korean (EUC-KR)"),                   "EUC-KR"        },
  72         {N_("Nordic (ISO-8859-10)"),              "ISO-8859-10"   },
  73         {N_("South European (ISO-8859-3)"),       "ISO-8859-3"    },
  74         {N_("Thai (TIS-620)"),                    "TIS-620"       },
  75         {N_("Turkish (IBM-857)"),                 "IBM857"        },
  76         {N_("Turkish (ISO-8859-9)"),              "ISO-8859-9"    },
  77         {N_("Turkish (Windows-1254)"),            "windows-1254"  },
  78         {N_("Unicode (UTF-7)"),                   "UTF-7"         },
  79         {N_("Unicode (UTF-8)"),                   "UTF-8"         },
  80         {N_("Unicode (UTF-16BE)"),                "UTF-16BE"      },
  81         {N_("Unicode (UTF-16LE)"),                "UTF-16LE"      },
  82         {N_("Unicode (UTF-32BE)"),                "UTF-32BE"      },
  83         {N_("Unicode (UTF-32LE)"),                "UTF-32LE"      },
  84         {N_("Vietnamese (VISCII)"),               "VISCII"        },
  85         {N_("Vietnamese (Windows-1258)"),         "windows-1258"  },
  86         {N_("Visual Hebrew (ISO-8859-8)"),        "ISO-8859-8"    },
  87         {N_("Western (IBM-850)"),                 "IBM850"        },
  88         {N_("Western (ISO-8859-1)"),              "ISO-8859-1"    },
  89         {N_("Western (ISO-8859-15)"),             "ISO-8859-15"   },
  90         {N_("Western (Windows-1252)"),            "windows-1252"  }
  91
  92         /*
  93          * From this point, character sets aren't supported by iconv
  94          */
  95 #if 0
  96         {N_("Arabic (IBM-864-I)"),                "IBM864i"              },
  97         {N_("Arabic (ISO-8859-6-E)"),             "ISO-8859-6-E"         },
  98         {N_("Arabic (ISO-8859-6-I)"),             "ISO-8859-6-I"         },
  99         {N_("Arabic (MacArabic)"),                "x-mac-arabic"         },
 100         {N_("Armenian (ARMSCII-8)"),              "armscii-8"            },
 101         {N_("Central European (MacCE)"),          "x-mac-ce"             },
 102         {N_("Chinese Simplified (GBK)"),          "x-gbk"                },
 103         {N_("Chinese Simplified (HZ)"),           "HZ-GB-2312"           },
 104         {N_("Chinese Traditional (EUC-TW)"),      "x-euc-tw"             },
 105         {N_("Croatian (MacCroatian)"),            "x-mac-croatian"       },
 106         {N_("Cyrillic (MacCyrillic)"),            "x-mac-cyrillic"       },
 107         {N_("Cyrillic/Ukrainian (MacUkrainian)"), "x-mac-ukrainian"      },
 108         {N_("Farsi (MacFarsi)"),                  "x-mac-farsi"},
 109         {N_("Greek (MacGreek)"),                  "x-mac-greek"          },
 110         {N_("Gujarati (MacGujarati)"),            "x-mac-gujarati"       },
 111         {N_("Gurmukhi (MacGurmukhi)"),            "x-mac-gurmukhi"       },
 112         {N_("Hebrew (ISO-8859-8-E)"),             "ISO-8859-8-E"         },
 113         {N_("Hebrew (ISO-8859-8-I)"),             "ISO-8859-8-I"         },
 114         {N_("Hebrew (MacHebrew)"),                "x-mac-hebrew"         },
 115         {N_("Hindi (MacDevanagari)"),             "x-mac-devanagari"     },
 116         {N_("Icelandic (MacIcelandic)"),          "x-mac-icelandic"      },
 117         {N_("Korean (JOHAB)"),                    "x-johab"              },
 118         {N_("Korean (UHC)"),                      "x-windows-949"        },
 119         {N_("Romanian (MacRomanian)"),            "x-mac-romanian"       },
 120         {N_("Turkish (MacTurkish)"),              "x-mac-turkish"        },
 121         {N_("User Defined"),                      "x-user-defined"       },
 122         {N_("Vietnamese (TCVN)"),                 "x-viet-tcvn5712"      },
 123         {N_("Vietnamese (VPS)"),                  "x-viet-vps"           },
 124         {N_("Western (MacRoman)"),                "x-mac-roman"          },
 125         /* charsets whithout posibly translatable names */
 126         {"T61.8bit",                              "T61.8bit"             },
 127         {"x-imap4-modified-utf7",                 "x-imap4-modified-utf7"},
 128         {"x-u-escaped",                           "x-u-escaped"          },
 129         {"windows-936",                           "windows-936"          }
 130 #endif
 131 };
 132
 133 /*************
 134  * Functions *
 135  *************/
 136
 137 /*
 138  * Commons conversion functions
 139  */
 140 char *convert_from_utf8_to_user(const char *string)
 141 {
 142         return FLAC_plugin__charset_convert_string(string, "UTF-8", flac_cfg.title.user_char_set);
 143 }
 144
 145 char *convert_from_user_to_utf8(const char *string)
 146 {
 147         return FLAC_plugin__charset_convert_string(string, flac_cfg.title.user_char_set, "UTF-8");
 148 }
 149
 150 GList *Charset_Create_List (void)
 151 {
 152         GList *list = NULL;
 153         guint i;
 154
 155         for (i=0; i<CHARSET_TRANS_ARRAY_LEN; i++)
 156                 list = g_list_append(list,_(charset_trans_array[i].charset_title));
 157         return list;
 158 }
 159
 160 GList *Charset_Create_List_UTF8_Only (void)
 161 {
 162         GList *list = NULL;
 163
 164         list = g_list_append(list,_(Charset_Get_Title_From_Name("UTF-8")));
 165         return list;
 166 }
 167
 168
 169 /*
 170  * Return charset_name from charset_title
 171  */
 172 gchar *Charset_Get_Name_From_Title (gchar *charset_title)
 173 {
 174         guint i;
 175
 176         if (charset_title)
 177                 for (i=0; i<CHARSET_TRANS_ARRAY_LEN; i++)
 178                         if ( strcasecmp(_(charset_title),_(charset_trans_array[i].charset_title)) == 0 )
 179                                 return charset_trans_array[i].charset_name;
 180         return "";
 181 }
 182
 183
 184 /*
 185  * Return charset_title from charset_name
 186  */
 187 gchar *Charset_Get_Title_From_Name (gchar *charset_name)
 188 {
 189         guint i;
 190
 191         if (charset_name)
 192                 for (i=0; i<CHARSET_TRANS_ARRAY_LEN; i++)
 193                         if ( strcasecmp(charset_name,charset_trans_array[i].charset_name) == 0 )
 194                                 return _(charset_trans_array[i].charset_title);
 195         return "";
 196 }