Dogcows Code - chaz/homebank/blob - src/hb-encoding.c

   1 /*  HomeBank -- Free, easy, personal accounting for everyone.
   2  *  Copyright (C) 1995-2016 Maxime DOYEN
   3  *
   4  *  This file is part of HomeBank.
   5  *
   6  *  HomeBank is free software; you can redistribute it and/or modify
   7  *  it under the terms of the GNU General Public License as published by
   8  *  the Free Software Foundation; either version 2 of the License, or
   9  *  (at your option) any later version.
  10  *
  11  *  HomeBank is distributed in the hope that it will be useful,
  12  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  *  GNU General Public License for more details.
  15  *
  16  *  You should have received a copy of the GNU General Public License
  17  *  along with this program.  If not, see <http://www.gnu.org/licenses/>.
  18  */
  19
  20 #include "homebank.h"
  21 #include "hb-encoding.h"
  22
  23 #define MYDEBUG 0
  24
  25 #if MYDEBUG
  26 #define DB(x) (x);
  27 #else
  28 #define DB(x);
  29 #endif
  30
  31 /* our global datas */
  32 extern struct HomeBank *GLOBALS;
  33
  34 /* = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = */
  35
  36
  37
  38 /*
  39  * The original versions of the following tables are taken from profterm
  40  *
  41  * Copyright (C) 2002 Red Hat, Inc.
  42  */
  43
  44
  45
  46 static const GeditEncoding utf8_encoding =  {
  47         GEDIT_ENCODING_UTF_8,
  48         "UTF-8",
  49         "Unicode"
  50 };
  51
  52 static const GeditEncoding encodings [] = {
  53
  54   { GEDIT_ENCODING_ISO_8859_1,
  55     "ISO-8859-1", "Western" },
  56   { GEDIT_ENCODING_ISO_8859_2,
  57    "ISO-8859-2", "Central European" },
  58   { GEDIT_ENCODING_ISO_8859_3,
  59     "ISO-8859-3", "South European" },
  60   { GEDIT_ENCODING_ISO_8859_4,
  61     "ISO-8859-4", "Baltic" },
  62   { GEDIT_ENCODING_ISO_8859_5,
  63     "ISO-8859-5", "Cyrillic" },
  64   { GEDIT_ENCODING_ISO_8859_6,
  65     "ISO-8859-6", "Arabic" },
  66   { GEDIT_ENCODING_ISO_8859_7,
  67     "ISO-8859-7", "Greek" },
  68   { GEDIT_ENCODING_ISO_8859_8,
  69     "ISO-8859-8", "Hebrew Visual" },
  70   { GEDIT_ENCODING_ISO_8859_8_I,
  71     "ISO-8859-8-I", "Hebrew" },
  72   { GEDIT_ENCODING_ISO_8859_9,
  73     "ISO-8859-9", "Turkish" },
  74   { GEDIT_ENCODING_ISO_8859_10,
  75     "ISO-8859-10", "Nordic" },
  76   { GEDIT_ENCODING_ISO_8859_13,
  77     "ISO-8859-13", "Baltic" },
  78   { GEDIT_ENCODING_ISO_8859_14,
  79     "ISO-8859-14", "Celtic" },
  80   { GEDIT_ENCODING_ISO_8859_15,
  81     "ISO-8859-15", "Western" },
  82   { GEDIT_ENCODING_ISO_8859_16,
  83     "ISO-8859-16", "Romanian" },
  84
  85   { GEDIT_ENCODING_UTF_7,
  86     "UTF-7", "Unicode" },
  87   { GEDIT_ENCODING_UTF_16,
  88     "UTF-16", "Unicode" },
  89   { GEDIT_ENCODING_UTF_16_BE,
  90     "UTF-16BE", "Unicode" },
  91   { GEDIT_ENCODING_UTF_16_LE,
  92     "UTF-16LE", "Unicode" },
  93   { GEDIT_ENCODING_UTF_32,
  94     "UTF-32", "Unicode" },
  95   { GEDIT_ENCODING_UCS_2,
  96     "UCS-2", "Unicode" },
  97   { GEDIT_ENCODING_UCS_4,
  98     "UCS-4", "Unicode" },
  99
 100   { GEDIT_ENCODING_ARMSCII_8,
 101     "ARMSCII-8", "Armenian" },
 102   { GEDIT_ENCODING_BIG5,
 103     "BIG5", "Chinese Traditional" },
 104   { GEDIT_ENCODING_BIG5_HKSCS,
 105     "BIG5-HKSCS", "Chinese Traditional" },
 106   { GEDIT_ENCODING_CP_866,
 107     "CP866", "Cyrillic/Russian" },
 108
 109   { GEDIT_ENCODING_EUC_JP,
 110     "EUC-JP", "Japanese" },
 111   { GEDIT_ENCODING_EUC_JP_MS,
 112     "EUC-JP-MS", "Japanese" },
 113   { GEDIT_ENCODING_CP932,
 114     "CP932", "Japanese" },
 115
 116   { GEDIT_ENCODING_EUC_KR,
 117     "EUC-KR", "Korean" },
 118   { GEDIT_ENCODING_EUC_TW,
 119     "EUC-TW", "Chinese Traditional" },
 120
 121   { GEDIT_ENCODING_GB18030,
 122     "GB18030", "Chinese Simplified" },
 123   { GEDIT_ENCODING_GB2312,
 124     "GB2312", "Chinese Simplified" },
 125   { GEDIT_ENCODING_GBK,
 126     "GBK", "Chinese Simplified" },
 127   { GEDIT_ENCODING_GEOSTD8,
 128     "GEORGIAN-ACADEMY", "Georgian" }, /* FIXME GEOSTD8 ? */
 129   { GEDIT_ENCODING_HZ,
 130     "HZ", "Chinese Simplified" },
 131
 132   { GEDIT_ENCODING_IBM_850,
 133     "IBM850", "Western" },
 134   { GEDIT_ENCODING_IBM_852,
 135     "IBM852", "Central European" },
 136   { GEDIT_ENCODING_IBM_855,
 137     "IBM855", "Cyrillic" },
 138   { GEDIT_ENCODING_IBM_857,
 139     "IBM857", "Turkish" },
 140   { GEDIT_ENCODING_IBM_862,
 141     "IBM862", "Hebrew" },
 142   { GEDIT_ENCODING_IBM_864,
 143     "IBM864", "Arabic" },
 144
 145   { GEDIT_ENCODING_ISO_2022_JP,
 146     "ISO-2022-JP", "Japanese" },
 147   { GEDIT_ENCODING_ISO_2022_KR,
 148     "ISO-2022-KR", "Korean" },
 149   { GEDIT_ENCODING_ISO_IR_111,
 150     "ISO-IR-111", "Cyrillic" },
 151   { GEDIT_ENCODING_JOHAB,
 152     "JOHAB", "Korean" },
 153   { GEDIT_ENCODING_KOI8_R,
 154     "KOI8R", "Cyrillic" },
 155   { GEDIT_ENCODING_KOI8__R,
 156     "KOI8-R", "Cyrillic" },
 157   { GEDIT_ENCODING_KOI8_U,
 158     "KOI8U", "Cyrillic/Ukrainian" },
 159
 160   { GEDIT_ENCODING_SHIFT_JIS,
 161     "SHIFT_JIS", "Japanese" },
 162   { GEDIT_ENCODING_TCVN,
 163     "TCVN", "Vietnamese" },
 164   { GEDIT_ENCODING_TIS_620,
 165     "TIS-620", "Thai" },
 166   { GEDIT_ENCODING_UHC,
 167     "UHC", "Korean" },
 168   { GEDIT_ENCODING_VISCII,
 169     "VISCII", "Vietnamese" },
 170
 171   { GEDIT_ENCODING_WINDOWS_1250,
 172     "WINDOWS-1250", "Central European" },
 173   { GEDIT_ENCODING_WINDOWS_1251,
 174     "WINDOWS-1251", "Cyrillic" },
 175   { GEDIT_ENCODING_WINDOWS_1252,
 176     "WINDOWS-1252", "Western" },
 177   { GEDIT_ENCODING_WINDOWS_1253,
 178     "WINDOWS-1253", "Greek" },
 179   { GEDIT_ENCODING_WINDOWS_1254,
 180     "WINDOWS-1254", "Turkish" },
 181   { GEDIT_ENCODING_WINDOWS_1255,
 182     "WINDOWS-1255", "Hebrew" },
 183   { GEDIT_ENCODING_WINDOWS_1256,
 184     "WINDOWS-1256", "Arabic" },
 185   { GEDIT_ENCODING_WINDOWS_1257,
 186     "WINDOWS-1257", "Baltic" },
 187   { GEDIT_ENCODING_WINDOWS_1258,
 188     "WINDOWS-1258", "Vietnamese" }
 189 };
 190
 191 const GeditEncoding *
 192 gedit_encoding_get_from_index (gint index)
 193 {
 194         //g_return_val_if_fail (index >= 0, NULL);
 195
 196         if (index >= GEDIT_ENCODING_LAST)
 197                 return NULL;
 198
 199         //gedit_encoding_lazy_init ();
 200
 201         return &encodings [index];
 202 }
 203
 204 const GeditEncoding *
 205 gedit_encoding_get_utf8 (void)
 206 {
 207         //gedit_encoding_lazy_init ();
 208
 209         return &utf8_encoding;
 210 }
 211
 212
 213 static gchar *homebank_utf8_convert(gchar *buffer, const gchar **charset)
 214 {
 215 GError *conv_error;
 216 gchar* conv_buffer = NULL;
 217 gsize new_len;
 218 guint i;
 219 gboolean valid;
 220 const struct _GeditEncoding *enc;
 221
 222         DB( g_print("(homebank) homebank_utf8_convert\n") );
 223
 224         for (i=0 ; i<GEDIT_ENCODING_LAST ; i++)
 225         {
 226                 conv_error = NULL;
 227
 228                 enc = gedit_encoding_get_from_index(i);
 229                 DB( g_print("-> should try %s\n",  enc->charset) );
 230
 231                 conv_buffer = g_convert(buffer, -1, "UTF-8", enc->charset, NULL, &new_len, &conv_error);
 232                 valid = g_utf8_validate (conv_buffer, -1, NULL);
 233                 if ((conv_error != NULL) || !valid )
 234                 {
 235                         DB( g_print ("  -> Couldn't convert from %s to UTF-8.\n", enc->charset) );
 236                 }
 237                 else
 238                 {
 239                         DB( g_print ("  -> file compatible with '%s'\n", enc->charset) );
 240                         if(charset != NULL)
 241                                 *charset = enc->charset;
 242                         return conv_buffer;
 243                 }
 244         }
 245
 246         if(charset != NULL)
 247                 *charset = NULL;
 248         return NULL;
 249 }
 250
 251
 252 /*
 253  * Ensure a buffer to be utf-8, and convert if necessary
 254  *
 255  */
 256 gchar *homebank_utf8_ensure(gchar *buffer)
 257 {
 258 gboolean isvalid;
 259 gchar *converted;
 260
 261         DB( g_print("(homebank) homebank_utf8_ensure\n") );
 262
 263         if(buffer == NULL)
 264                 return NULL;
 265
 266         isvalid = g_utf8_validate(buffer, -1, NULL);
 267         DB( g_print(" -> is valid utf8: %d\n", isvalid) );
 268
 269         if(!isvalid)
 270         {
 271                 converted = homebank_utf8_convert(buffer, NULL);
 272                 if(converted != NULL)
 273                 {
 274                         //g_warn here ?
 275                         g_free(buffer);
 276                         return converted;
 277                 }
 278                 //g_warn here ?
 279         }
 280         return buffer;
 281 }
 282
 283
 284 const gchar *homebank_file_getencoding(gchar *filename)
 285 {
 286 const gchar *charset = NULL;
 287 gchar *buffer;
 288 gsize length;
 289 GError *error = NULL;
 290 gboolean isutf8;
 291 const gchar *locale_charset;
 292 const struct _GeditEncoding *enc;
 293
 294         DB( g_print("(homebank) test encoding\n") );
 295
 296         if (g_get_charset (&locale_charset) == FALSE)
 297         {
 298                 //unknown_encoding.charset = g_strdup (locale_charset);
 299
 300         }
 301
 302         DB( g_print(" -> locale charset is '%s'\n", locale_charset) );
 303
 304         if (g_file_get_contents (filename, &buffer, &length, &error))
 305         {
 306
 307                 isutf8 = g_utf8_validate(buffer, -1, NULL);
 308                 DB( g_print(" -> is valid utf8: %d\n", isutf8) );
 309
 310                 if( isutf8 == FALSE )
 311                 {
 312                 gchar *converted;
 313
 314                         converted = homebank_utf8_convert(buffer, &charset);
 315
 316                         DB( g_print(" -> converted charset match: '%s'\n", charset) );
 317                         DB( g_print(" -> converted: '%p' %s\n", converted, converted) );
 318
 319                         if(converted != NULL)
 320                                 g_free(converted);
 321                 }
 322                 else
 323                 {
 324                         enc = gedit_encoding_get_utf8();
 325                         charset = enc->charset;
 326                 }
 327
 328
 329                 g_free(buffer);
 330         }
 331
 332         DB( g_print ("  -> charset is '%s'\n", charset) );
 333
 334         return charset;
 335 }
 336
 337