1 /* Text conversion from one charset to another.
3 Copyright (C) 2001 Walery Studennikov <despair@sama.ru>
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 2 of the License, or
8 (at your option) any later version.
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.
15 You should have received a copy of the GNU General Public License
16 along with this program; if not, write to the Free Software
17 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
21 * \brief Source: Text conversion from one charset to another
32 #include "lib/global.h"
33 #include "lib/strutil.h" /* utf-8 functions */
34 #include "lib/fileloc.h"
39 GPtrArray
*codepages
= NULL
;
41 unsigned char conv_displ
[256];
42 unsigned char conv_input
[256];
44 const char *cp_display
= NULL
;
45 const char *cp_source
= NULL
;
47 static codepage_desc
*
48 new_codepage_desc (const char *id
, const char *name
)
52 desc
= g_new (codepage_desc
, 1);
53 desc
->id
= g_strdup (id
);
54 desc
->name
= g_strdup (name
);
60 free_codepage_desc (gpointer data
, gpointer user_data
)
62 codepage_desc
*desc
= (codepage_desc
*) data
;
70 /* returns display codepage */
72 load_codepages_list_from_file (GPtrArray
**list
, const char *fname
)
77 char *default_codepage
= NULL
;
79 f
= fopen (fname
, "r");
83 for (i
= 0; fgets (buf
, sizeof buf
, f
) != NULL
; )
85 /* split string into id and cpname */
87 size_t buflen
= strlen (buf
);
89 if (*p
== '\n' || *p
== '\0' || *p
== '#')
92 if (buflen
> 0 && buf
[buflen
- 1] == '\n')
93 buf
[buflen
- 1] = '\0';
94 while (*p
!= '\t' && *p
!= ' ' && *p
!= '\0')
104 if (strcmp (buf
, "default") == 0)
105 default_codepage
= g_strdup (p
);
108 const char *id
= buf
;
112 *list
= g_ptr_array_sized_new (16);
113 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
120 /* whether id is already present in list */
121 /* if yes, overwrite description */
122 for (i
= 0; i
< (*list
)->len
; i
++)
126 desc
= (codepage_desc
*) g_ptr_array_index (*list
, i
);
128 if (strcmp (id
, desc
->id
) == 0)
132 desc
->name
= g_strdup (p
);
138 if (i
== (*list
)->len
)
139 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
144 if (default_codepage
!= NULL
)
146 display_codepage
= get_codepage_index (default_codepage
);
147 g_free (default_codepage
);
155 load_codepages_list (void)
160 /* 1: try load /usr/share/mc/mc.charsets */
161 fname
= g_build_filename (mc_home_alt
, CHARSETS_LIST
, (char *) NULL
);
162 load_codepages_list_from_file (&codepages
, fname
);
165 /* 2: try load /etc/mc/mc.charsets */
166 fname
= g_build_filename (mc_home
, CHARSETS_LIST
, (char *) NULL
);
167 load_codepages_list_from_file (&codepages
, fname
);
170 if (codepages
== NULL
)
172 /* files are not found, add defaullt codepage */
173 fprintf (stderr
, "%s\n", _("Warning: cannot load codepages list"));
175 codepages
= g_ptr_array_new ();
176 g_ptr_array_add (codepages
, new_codepage_desc ("ASCII", _("7-bit ASCII")));
181 free_codepages_list (void)
183 g_ptr_array_foreach (codepages
, free_codepage_desc
, NULL
);
184 g_ptr_array_free (codepages
, TRUE
);
187 #define OTHER_8BIT "Other_8_bit"
190 get_codepage_id (const int n
)
192 return (n
< 0) ? OTHER_8BIT
: ((codepage_desc
*) g_ptr_array_index (codepages
, n
))->id
;
196 get_codepage_index (const char *id
)
199 if (strcmp (id
, OTHER_8BIT
) == 0)
201 if (codepages
== NULL
)
203 for (i
= 0; i
< codepages
->len
; i
++)
204 if (strcmp (id
, ((codepage_desc
*) g_ptr_array_index (codepages
, i
))->id
) == 0)
209 /** Check if specified encoding can be used in mc.
210 * @param encoding name of encoding
211 * @returns TRUE if encoding has supported by mc, FALSE otherwise
214 is_supported_encoding (const char *encoding
)
216 gboolean result
= FALSE
;
219 for (t
= 0; t
< codepages
->len
; t
++)
221 const char *id
= ((codepage_desc
*) g_ptr_array_index (codepages
, t
))->id
;
222 result
|= (g_ascii_strncasecmp (encoding
, id
, strlen (id
)) == 0);
229 translate_character (GIConv cd
, char c
)
231 gchar
*tmp_buff
= NULL
;
232 gsize bytes_read
, bytes_written
= 0;
233 const char *ibuf
= &c
;
238 tmp_buff
= g_convert_with_iconv (ibuf
, ibuflen
, cd
, &bytes_read
, &bytes_written
, NULL
);
246 * FIXME: This assumes that ASCII is always the first encoding
252 init_translation_table (int cpsource
, int cpdisplay
)
257 /* Fill inpit <-> display tables */
259 if (cpsource
< 0 || cpdisplay
< 0 || cpsource
== cpdisplay
) {
260 for (i
= 0; i
<= 255; ++i
) {
263 cp_source
= cp_display
;
268 for (i
= 0; i
<= 127; ++i
) {
272 cp_source
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpsource
))->id
;
273 cp_display
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpdisplay
))->id
;
275 /* display <- inpit table */
277 cd
= g_iconv_open (cp_display
, cp_source
);
278 if (cd
== INVALID_CONV
)
279 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_source
, cp_display
);
281 for (i
= 128; i
<= 255; ++i
)
282 conv_displ
[i
] = translate_character (cd
, i
);
286 /* inpit <- display table */
288 cd
= g_iconv_open (cp_source
, cp_display
);
289 if (cd
== INVALID_CONV
)
290 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_display
, cp_source
);
292 for (i
= 128; i
<= 255; ++i
) {
294 ch
= translate_character (cd
, i
);
295 conv_input
[i
] = (ch
== UNKNCHAR
) ? i
: ch
;
304 convert_to_display (char *str
)
310 *str
= conv_displ
[(unsigned char) *str
];
316 str_convert_to_display (char *str
)
318 return str_nconvert_to_display (str
, -1);
323 str_nconvert_to_display (char *str
, int len
)
329 return g_string_new("");
331 if (cp_display
== cp_source
)
332 return g_string_new(str
);
334 conv
= str_crt_conv_from (cp_source
);
336 buff
= g_string_new("");
337 str_nconvert (conv
, str
, len
, buff
);
338 str_close_conv (conv
);
343 convert_from_input (char *str
)
349 *str
= conv_input
[(unsigned char) *str
];
355 str_convert_to_input (char *str
)
357 return str_nconvert_to_input (str
, -1);
361 str_nconvert_to_input (char *str
, int len
)
367 return g_string_new("");
369 if (cp_display
== cp_source
)
370 return g_string_new(str
);
372 conv
= str_crt_conv_to (cp_source
);
374 buff
= g_string_new("");
375 str_nconvert (conv
, str
, len
, buff
);
376 str_close_conv (conv
);
381 convert_from_utf_to_current (const char *str
)
383 unsigned char buf_ch
[6 + 1];
384 unsigned char ch
= '.';
391 cp_to
= get_codepage_id ( source_codepage
);
392 conv
= str_crt_conv_to ( cp_to
);
394 if (conv
!= INVALID_CONV
) {
395 switch (str_translate_char (conv
, str
, -1, (char *)buf_ch
, sizeof(buf_ch
))) {
404 str_close_conv (conv
);
412 convert_from_utf_to_current_c (const int input_char
, GIConv conv
)
414 unsigned char str
[6 + 1];
415 unsigned char buf_ch
[6 + 1];
416 unsigned char ch
= '.';
420 res
= g_unichar_to_utf8 (input_char
, (char *)str
);
426 switch (str_translate_char (conv
, (char *)str
, -1, (char *)buf_ch
, sizeof(buf_ch
))) {
439 convert_from_8bit_to_utf_c (const char input_char
, GIConv conv
)
441 unsigned char str
[2];
442 unsigned char buf_ch
[6 + 1];
446 str
[0] = (unsigned char) input_char
;
449 switch (str_translate_char (conv
, (char *)str
, -1, (char *)buf_ch
, sizeof(buf_ch
))) {
451 res
= g_utf8_get_char_validated ((char *)buf_ch
, -1);
467 convert_from_8bit_to_utf_c2 (const char input_char
)
469 unsigned char str
[2];
470 unsigned char buf_ch
[6 + 1];
476 str
[0] = (unsigned char) input_char
;
479 cp_from
= get_codepage_id ( source_codepage
);
480 conv
= str_crt_conv_to (cp_from
);
482 if (conv
!= INVALID_CONV
) {
483 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof(buf_ch
))) {
485 res
= g_utf8_get_char_validated ((char *) buf_ch
, -1);
497 str_close_conv (conv
);
502 #endif /* HAVE_CHARSET */