2 Text conversion from one charset to another.
4 Copyright (C) 2001-2024
5 Free Software Foundation, Inc.
8 Walery Studennikov <despair@sama.ru>
10 This file is part of the Midnight Commander.
12 The Midnight Commander is free software: you can redistribute it
13 and/or modify it under the terms of the GNU General Public License as
14 published by the Free Software Foundation, either version 3 of the License,
15 or (at your option) any later version.
17 The Midnight Commander is distributed in the hope that it will be useful,
18 but WITHOUT ANY WARRANTY; without even the implied warranty of
19 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20 GNU General Public License for more details.
22 You should have received a copy of the GNU General Public License
23 along with this program. If not, see <http://www.gnu.org/licenses/>.
27 * \brief Source: Text conversion from one charset to another
36 #include "lib/global.h"
37 #include "lib/strutil.h" /* utf-8 functions */
38 #include "lib/fileloc.h"
39 #include "lib/util.h" /* whitespace() */
41 #include "lib/charsets.h"
43 /*** global variables ****************************************************************************/
45 GPtrArray
*codepages
= NULL
;
47 unsigned char conv_displ
[256];
48 unsigned char conv_input
[256];
50 const char *cp_display
= NULL
;
51 const char *cp_source
= NULL
;
53 /*** file scope macro definitions ****************************************************************/
55 #define UNKNCHAR '\001'
57 #define OTHER_8BIT "Other_8_bit"
59 /*** file scope type declarations ****************************************************************/
61 /*** forward declarations (file scope functions) *************************************************/
63 /*** file scope variables ************************************************************************/
65 /* --------------------------------------------------------------------------------------------- */
66 /*** file scope functions ************************************************************************/
67 /* --------------------------------------------------------------------------------------------- */
69 static codepage_desc
*
70 new_codepage_desc (const char *id
, const char *name
)
74 desc
= g_new (codepage_desc
, 1);
75 desc
->id
= g_strdup (id
);
76 desc
->name
= g_strdup (name
);
81 /* --------------------------------------------------------------------------------------------- */
84 free_codepage_desc (gpointer data
)
86 codepage_desc
*desc
= (codepage_desc
*) data
;
93 /* --------------------------------------------------------------------------------------------- */
94 /* returns display codepage */
97 load_codepages_list_from_file (GPtrArray
** list
, const char *fname
)
100 char buf
[BUF_MEDIUM
];
101 char *default_codepage
= NULL
;
103 f
= fopen (fname
, "r");
107 while (fgets (buf
, sizeof buf
, f
) != NULL
)
109 /* split string into id and cpname */
113 if (*p
== '\n' || *p
== '\0' || *p
== '#')
116 buflen
= strlen (buf
);
118 if (buflen
!= 0 && buf
[buflen
- 1] == '\n')
119 buf
[buflen
- 1] = '\0';
120 while (*p
!= '\0' && !whitespace (*p
))
130 if (strcmp (buf
, "default") == 0)
131 default_codepage
= g_strdup (p
);
134 const char *id
= buf
;
138 *list
= g_ptr_array_sized_new (16);
139 g_ptr_array_set_free_func (*list
, free_codepage_desc
);
140 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
146 /* whether id is already present in list */
147 /* if yes, overwrite description */
148 for (i
= 0; i
< (*list
)->len
; i
++)
152 desc
= (codepage_desc
*) g_ptr_array_index (*list
, i
);
154 if (strcmp (id
, desc
->id
) == 0)
158 desc
->name
= g_strdup (p
);
164 if (i
== (*list
)->len
)
165 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
170 if (default_codepage
!= NULL
)
172 mc_global
.display_codepage
= get_codepage_index (default_codepage
);
173 g_free (default_codepage
);
180 /* --------------------------------------------------------------------------------------------- */
183 translate_character (GIConv cd
, char c
)
185 gchar
*tmp_buff
= NULL
;
186 gsize bytes_read
, bytes_written
= 0;
187 const char *ibuf
= &c
;
191 tmp_buff
= g_convert_with_iconv (ibuf
, ibuflen
, cd
, &bytes_read
, &bytes_written
, NULL
);
192 if (tmp_buff
!= NULL
)
198 /* --------------------------------------------------------------------------------------------- */
199 /*** public functions ****************************************************************************/
200 /* --------------------------------------------------------------------------------------------- */
203 load_codepages_list (void)
207 /* 1: try load /usr/share/mc/mc.charsets */
208 fname
= g_build_filename (mc_global
.share_data_dir
, CHARSETS_LIST
, (char *) NULL
);
209 load_codepages_list_from_file (&codepages
, fname
);
212 /* 2: try load /etc/mc/mc.charsets */
213 fname
= g_build_filename (mc_global
.sysconfig_dir
, CHARSETS_LIST
, (char *) NULL
);
214 load_codepages_list_from_file (&codepages
, fname
);
217 if (codepages
== NULL
)
219 /* files are not found, add default codepage */
220 fprintf (stderr
, "%s\n", _("Warning: cannot load codepages list"));
222 codepages
= g_ptr_array_new_with_free_func (free_codepage_desc
);
223 g_ptr_array_add (codepages
, new_codepage_desc (DEFAULT_CHARSET
, _("7-bit ASCII")));
227 /* --------------------------------------------------------------------------------------------- */
230 free_codepages_list (void)
232 g_ptr_array_free (codepages
, TRUE
);
233 /* NULL-ize pointer to make unit tests happy */
237 /* --------------------------------------------------------------------------------------------- */
240 get_codepage_id (const int n
)
242 return (n
< 0) ? OTHER_8BIT
: ((codepage_desc
*) g_ptr_array_index (codepages
, n
))->id
;
245 /* --------------------------------------------------------------------------------------------- */
248 get_codepage_index (const char *id
)
252 if (codepages
== NULL
)
254 if (strcmp (id
, OTHER_8BIT
) == 0)
256 for (i
= 0; i
< codepages
->len
; i
++)
257 if (strcmp (id
, ((codepage_desc
*) g_ptr_array_index (codepages
, i
))->id
) == 0)
262 /* --------------------------------------------------------------------------------------------- */
263 /** Check if specified encoding can be used in mc.
264 * @param encoding name of encoding
265 * @return TRUE if encoding is supported by mc, FALSE otherwise
269 is_supported_encoding (const char *encoding
)
271 gboolean result
= FALSE
;
274 for (t
= 0; t
< codepages
->len
; t
++)
278 id
= ((codepage_desc
*) g_ptr_array_index (codepages
, t
))->id
;
279 result
|= (g_ascii_strncasecmp (encoding
, id
, strlen (id
)) == 0);
285 /* --------------------------------------------------------------------------------------------- */
288 init_translation_table (int cpsource
, int cpdisplay
)
293 /* Fill inpit <-> display tables */
295 if (cpsource
< 0 || cpdisplay
< 0 || cpsource
== cpdisplay
)
297 for (i
= 0; i
<= 255; ++i
)
302 cp_source
= cp_display
;
306 for (i
= 0; i
<= 127; ++i
)
311 cp_source
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpsource
))->id
;
312 cp_display
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpdisplay
))->id
;
314 /* display <- inpit table */
316 cd
= g_iconv_open (cp_display
, cp_source
);
317 if (cd
== INVALID_CONV
)
318 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_source
, cp_display
);
320 for (i
= 128; i
<= 255; ++i
)
321 conv_displ
[i
] = translate_character (cd
, i
);
325 /* inpit <- display table */
327 cd
= g_iconv_open (cp_source
, cp_display
);
328 if (cd
== INVALID_CONV
)
329 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_display
, cp_source
);
331 for (i
= 128; i
<= 255; ++i
)
334 ch
= translate_character (cd
, i
);
335 conv_input
[i
] = (ch
== UNKNCHAR
) ? i
: ch
;
343 /* --------------------------------------------------------------------------------------------- */
346 convert_to_display (char *str
)
349 for (; *str
!= '\0'; str
++)
350 *str
= conv_displ
[(unsigned char) *str
];
353 /* --------------------------------------------------------------------------------------------- */
356 str_nconvert_to_display (const char *str
, int len
)
364 if (cp_display
== cp_source
)
365 return g_string_new (str
);
367 conv
= str_crt_conv_from (cp_source
);
369 buff
= g_string_new ("");
370 str_nconvert (conv
, str
, len
, buff
);
371 str_close_conv (conv
);
375 /* --------------------------------------------------------------------------------------------- */
378 convert_from_input (char *str
)
381 for (; *str
!= '\0'; str
++)
382 *str
= conv_input
[(unsigned char) *str
];
385 /* --------------------------------------------------------------------------------------------- */
388 str_nconvert_to_input (const char *str
, int len
)
396 if (cp_display
== cp_source
)
397 return g_string_new (str
);
399 conv
= str_crt_conv_to (cp_source
);
401 buff
= g_string_new ("");
402 str_nconvert (conv
, str
, len
, buff
);
403 str_close_conv (conv
);
407 /* --------------------------------------------------------------------------------------------- */
410 convert_from_utf_to_current (const char *str
)
412 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
413 unsigned char ch
= '.';
420 cp_to
= get_codepage_id (mc_global
.source_codepage
);
421 conv
= str_crt_conv_to (cp_to
);
423 if (conv
!= INVALID_CONV
)
425 switch (str_translate_char (conv
, str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
437 str_close_conv (conv
);
443 /* --------------------------------------------------------------------------------------------- */
446 convert_from_utf_to_current_c (int input_char
, GIConv conv
)
448 unsigned char str
[UTF8_CHAR_LEN
+ 1];
449 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
450 unsigned char ch
= '.';
453 res
= g_unichar_to_utf8 (input_char
, (char *) str
);
459 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
475 /* --------------------------------------------------------------------------------------------- */
478 convert_from_8bit_to_utf_c (char input_char
, GIConv conv
)
480 unsigned char str
[2];
481 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
484 str
[0] = (unsigned char) input_char
;
487 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
493 res
= g_utf8_get_char_validated ((char *) buf_ch
, -1);
494 ch
= res
>= 0 ? res
: buf_ch
[0];
507 /* --------------------------------------------------------------------------------------------- */
510 convert_from_8bit_to_utf_c2 (char input_char
)
516 cp_from
= get_codepage_id (mc_global
.source_codepage
);
518 conv
= str_crt_conv_to (cp_from
);
519 if (conv
!= INVALID_CONV
)
521 ch
= convert_from_8bit_to_utf_c (input_char
, conv
);
522 str_close_conv (conv
);
528 /* --------------------------------------------------------------------------------------------- */