2 Text conversion from one charset to another.
4 Copyright (C) 2001-2018
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 /*** file scope variables ************************************************************************/
63 /*** file scope functions ************************************************************************/
64 /* --------------------------------------------------------------------------------------------- */
66 static codepage_desc
*
67 new_codepage_desc (const char *id
, const char *name
)
71 desc
= g_new (codepage_desc
, 1);
72 desc
->id
= g_strdup (id
);
73 desc
->name
= g_strdup (name
);
78 /* --------------------------------------------------------------------------------------------- */
81 free_codepage_desc (gpointer data
, gpointer user_data
)
83 codepage_desc
*desc
= (codepage_desc
*) data
;
91 /* --------------------------------------------------------------------------------------------- */
92 /* returns display codepage */
95 load_codepages_list_from_file (GPtrArray
** list
, const char *fname
)
99 char *default_codepage
= NULL
;
101 f
= fopen (fname
, "r");
105 while (fgets (buf
, sizeof buf
, f
) != NULL
)
107 /* split string into id and cpname */
111 if (*p
== '\n' || *p
== '\0' || *p
== '#')
114 buflen
= strlen (buf
);
116 if (buflen
!= 0 && buf
[buflen
- 1] == '\n')
117 buf
[buflen
- 1] = '\0';
118 while (*p
!= '\0' && !whitespace (*p
))
128 if (strcmp (buf
, "default") == 0)
129 default_codepage
= g_strdup (p
);
132 const char *id
= buf
;
136 *list
= g_ptr_array_sized_new (16);
137 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
143 /* whether id is already present in list */
144 /* if yes, overwrite description */
145 for (i
= 0; i
< (*list
)->len
; i
++)
149 desc
= (codepage_desc
*) g_ptr_array_index (*list
, i
);
151 if (strcmp (id
, desc
->id
) == 0)
155 desc
->name
= g_strdup (p
);
161 if (i
== (*list
)->len
)
162 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
167 if (default_codepage
!= NULL
)
169 mc_global
.display_codepage
= get_codepage_index (default_codepage
);
170 g_free (default_codepage
);
177 /* --------------------------------------------------------------------------------------------- */
180 translate_character (GIConv cd
, char c
)
182 gchar
*tmp_buff
= NULL
;
183 gsize bytes_read
, bytes_written
= 0;
184 const char *ibuf
= &c
;
188 tmp_buff
= g_convert_with_iconv (ibuf
, ibuflen
, cd
, &bytes_read
, &bytes_written
, NULL
);
189 if (tmp_buff
!= NULL
)
195 /* --------------------------------------------------------------------------------------------- */
196 /*** public functions ****************************************************************************/
197 /* --------------------------------------------------------------------------------------------- */
200 load_codepages_list (void)
204 /* 1: try load /usr/share/mc/mc.charsets */
205 fname
= g_build_filename (mc_global
.share_data_dir
, CHARSETS_LIST
, (char *) NULL
);
206 load_codepages_list_from_file (&codepages
, fname
);
209 /* 2: try load /etc/mc/mc.charsets */
210 fname
= g_build_filename (mc_global
.sysconfig_dir
, CHARSETS_LIST
, (char *) NULL
);
211 load_codepages_list_from_file (&codepages
, fname
);
214 if (codepages
== NULL
)
216 /* files are not found, add defaullt codepage */
217 fprintf (stderr
, "%s\n", _("Warning: cannot load codepages list"));
219 codepages
= g_ptr_array_new ();
220 g_ptr_array_add (codepages
, new_codepage_desc (DEFAULT_CHARSET
, _("7-bit ASCII")));
224 /* --------------------------------------------------------------------------------------------- */
227 free_codepages_list (void)
229 g_ptr_array_foreach (codepages
, free_codepage_desc
, NULL
);
230 g_ptr_array_free (codepages
, TRUE
);
231 /* NULL-ize pointer to make unit tests happy */
235 /* --------------------------------------------------------------------------------------------- */
238 get_codepage_id (const int n
)
240 return (n
< 0) ? OTHER_8BIT
: ((codepage_desc
*) g_ptr_array_index (codepages
, n
))->id
;
243 /* --------------------------------------------------------------------------------------------- */
246 get_codepage_index (const char *id
)
250 if (codepages
== NULL
)
252 if (strcmp (id
, OTHER_8BIT
) == 0)
254 for (i
= 0; i
< codepages
->len
; i
++)
255 if (strcmp (id
, ((codepage_desc
*) g_ptr_array_index (codepages
, i
))->id
) == 0)
260 /* --------------------------------------------------------------------------------------------- */
261 /** Check if specified encoding can be used in mc.
262 * @param encoding name of encoding
263 * @return TRUE if encoding is supported by mc, FALSE otherwise
267 is_supported_encoding (const char *encoding
)
269 gboolean result
= FALSE
;
272 for (t
= 0; t
< codepages
->len
; t
++)
276 id
= ((codepage_desc
*) g_ptr_array_index (codepages
, t
))->id
;
277 result
|= (g_ascii_strncasecmp (encoding
, id
, strlen (id
)) == 0);
283 /* --------------------------------------------------------------------------------------------- */
286 init_translation_table (int cpsource
, int cpdisplay
)
291 /* Fill inpit <-> display tables */
293 if (cpsource
< 0 || cpdisplay
< 0 || cpsource
== cpdisplay
)
295 for (i
= 0; i
<= 255; ++i
)
300 cp_source
= cp_display
;
304 for (i
= 0; i
<= 127; ++i
)
309 cp_source
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpsource
))->id
;
310 cp_display
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpdisplay
))->id
;
312 /* display <- inpit table */
314 cd
= g_iconv_open (cp_display
, cp_source
);
315 if (cd
== INVALID_CONV
)
316 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_source
, cp_display
);
318 for (i
= 128; i
<= 255; ++i
)
319 conv_displ
[i
] = translate_character (cd
, i
);
323 /* inpit <- display table */
325 cd
= g_iconv_open (cp_source
, cp_display
);
326 if (cd
== INVALID_CONV
)
327 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_display
, cp_source
);
329 for (i
= 128; i
<= 255; ++i
)
332 ch
= translate_character (cd
, i
);
333 conv_input
[i
] = (ch
== UNKNCHAR
) ? i
: ch
;
341 /* --------------------------------------------------------------------------------------------- */
344 convert_to_display (char *str
)
347 for (; *str
!= '\0'; str
++)
348 *str
= conv_displ
[(unsigned char) *str
];
351 /* --------------------------------------------------------------------------------------------- */
354 str_convert_to_display (const char *str
)
356 return str_nconvert_to_display (str
, -1);
359 /* --------------------------------------------------------------------------------------------- */
362 str_nconvert_to_display (const char *str
, int len
)
368 return g_string_new ("");
370 if (cp_display
== cp_source
)
371 return g_string_new (str
);
373 conv
= str_crt_conv_from (cp_source
);
375 buff
= g_string_new ("");
376 str_nconvert (conv
, str
, len
, buff
);
377 str_close_conv (conv
);
381 /* --------------------------------------------------------------------------------------------- */
384 convert_from_input (char *str
)
387 for (; *str
!= '\0'; str
++)
388 *str
= conv_input
[(unsigned char) *str
];
391 /* --------------------------------------------------------------------------------------------- */
394 str_convert_to_input (const char *str
)
396 return str_nconvert_to_input (str
, -1);
399 /* --------------------------------------------------------------------------------------------- */
402 str_nconvert_to_input (const char *str
, int len
)
408 return g_string_new ("");
410 if (cp_display
== cp_source
)
411 return g_string_new (str
);
413 conv
= str_crt_conv_to (cp_source
);
415 buff
= g_string_new ("");
416 str_nconvert (conv
, str
, len
, buff
);
417 str_close_conv (conv
);
421 /* --------------------------------------------------------------------------------------------- */
424 convert_from_utf_to_current (const char *str
)
426 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
427 unsigned char ch
= '.';
434 cp_to
= get_codepage_id (mc_global
.source_codepage
);
435 conv
= str_crt_conv_to (cp_to
);
437 if (conv
!= INVALID_CONV
)
439 switch (str_translate_char (conv
, str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
451 str_close_conv (conv
);
457 /* --------------------------------------------------------------------------------------------- */
460 convert_from_utf_to_current_c (int input_char
, GIConv conv
)
462 unsigned char str
[UTF8_CHAR_LEN
+ 1];
463 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
464 unsigned char ch
= '.';
467 res
= g_unichar_to_utf8 (input_char
, (char *) str
);
473 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
489 /* --------------------------------------------------------------------------------------------- */
492 convert_from_8bit_to_utf_c (char input_char
, GIConv conv
)
494 unsigned char str
[2];
495 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
498 str
[0] = (unsigned char) input_char
;
501 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
507 res
= g_utf8_get_char_validated ((char *) buf_ch
, -1);
508 ch
= res
>= 0 ? res
: buf_ch
[0];
521 /* --------------------------------------------------------------------------------------------- */
524 convert_from_8bit_to_utf_c2 (char input_char
)
530 cp_from
= get_codepage_id (mc_global
.source_codepage
);
532 conv
= str_crt_conv_to (cp_from
);
533 if (conv
!= INVALID_CONV
)
535 ch
= convert_from_8bit_to_utf_c (input_char
, conv
);
536 str_close_conv (conv
);
542 /* --------------------------------------------------------------------------------------------- */