2 Text conversion from one charset to another.
4 Copyright (C) 2001-2017
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 */
109 size_t buflen
= strlen (buf
);
111 if (*p
== '\n' || *p
== '\0' || *p
== '#')
114 if (buflen
> 0 && buf
[buflen
- 1] == '\n')
115 buf
[buflen
- 1] = '\0';
116 while (*p
!= '\0' && !whitespace (*p
))
126 if (strcmp (buf
, "default") == 0)
127 default_codepage
= g_strdup (p
);
130 const char *id
= buf
;
134 *list
= g_ptr_array_sized_new (16);
135 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
141 /* whether id is already present in list */
142 /* if yes, overwrite description */
143 for (i
= 0; i
< (*list
)->len
; i
++)
147 desc
= (codepage_desc
*) g_ptr_array_index (*list
, i
);
149 if (strcmp (id
, desc
->id
) == 0)
153 desc
->name
= g_strdup (p
);
159 if (i
== (*list
)->len
)
160 g_ptr_array_add (*list
, new_codepage_desc (id
, p
));
165 if (default_codepage
!= NULL
)
167 mc_global
.display_codepage
= get_codepage_index (default_codepage
);
168 g_free (default_codepage
);
175 /* --------------------------------------------------------------------------------------------- */
178 translate_character (GIConv cd
, char c
)
180 gchar
*tmp_buff
= NULL
;
181 gsize bytes_read
, bytes_written
= 0;
182 const char *ibuf
= &c
;
187 tmp_buff
= g_convert_with_iconv (ibuf
, ibuflen
, cd
, &bytes_read
, &bytes_written
, NULL
);
194 /* --------------------------------------------------------------------------------------------- */
195 /*** public functions ****************************************************************************/
196 /* --------------------------------------------------------------------------------------------- */
199 load_codepages_list (void)
203 /* 1: try load /usr/share/mc/mc.charsets */
204 fname
= g_build_filename (mc_global
.share_data_dir
, CHARSETS_LIST
, (char *) NULL
);
205 load_codepages_list_from_file (&codepages
, fname
);
208 /* 2: try load /etc/mc/mc.charsets */
209 fname
= g_build_filename (mc_global
.sysconfig_dir
, CHARSETS_LIST
, (char *) NULL
);
210 load_codepages_list_from_file (&codepages
, fname
);
213 if (codepages
== NULL
)
215 /* files are not found, add defaullt codepage */
216 fprintf (stderr
, "%s\n", _("Warning: cannot load codepages list"));
218 codepages
= g_ptr_array_new ();
219 g_ptr_array_add (codepages
, new_codepage_desc (DEFAULT_CHARSET
, _("7-bit ASCII")));
223 /* --------------------------------------------------------------------------------------------- */
226 free_codepages_list (void)
228 g_ptr_array_foreach (codepages
, free_codepage_desc
, NULL
);
229 g_ptr_array_free (codepages
, TRUE
);
230 /* NULL-ize pointer to make unit tests happy */
234 /* --------------------------------------------------------------------------------------------- */
237 get_codepage_id (const int n
)
239 return (n
< 0) ? OTHER_8BIT
: ((codepage_desc
*) g_ptr_array_index (codepages
, n
))->id
;
242 /* --------------------------------------------------------------------------------------------- */
245 get_codepage_index (const char *id
)
248 if (strcmp (id
, OTHER_8BIT
) == 0)
250 if (codepages
== NULL
)
252 for (i
= 0; i
< codepages
->len
; i
++)
253 if (strcmp (id
, ((codepage_desc
*) g_ptr_array_index (codepages
, i
))->id
) == 0)
258 /* --------------------------------------------------------------------------------------------- */
259 /** Check if specified encoding can be used in mc.
260 * @param encoding name of encoding
261 * @return TRUE if encoding is supported by mc, FALSE otherwise
265 is_supported_encoding (const char *encoding
)
267 gboolean result
= FALSE
;
270 for (t
= 0; t
< codepages
->len
; t
++)
272 const char *id
= ((codepage_desc
*) g_ptr_array_index (codepages
, t
))->id
;
273 result
|= (g_ascii_strncasecmp (encoding
, id
, strlen (id
)) == 0);
279 /* --------------------------------------------------------------------------------------------- */
282 init_translation_table (int cpsource
, int cpdisplay
)
287 /* Fill inpit <-> display tables */
289 if (cpsource
< 0 || cpdisplay
< 0 || cpsource
== cpdisplay
)
291 for (i
= 0; i
<= 255; ++i
)
295 cp_source
= cp_display
;
300 for (i
= 0; i
<= 127; ++i
)
305 cp_source
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpsource
))->id
;
306 cp_display
= ((codepage_desc
*) g_ptr_array_index (codepages
, cpdisplay
))->id
;
308 /* display <- inpit table */
310 cd
= g_iconv_open (cp_display
, cp_source
);
311 if (cd
== INVALID_CONV
)
312 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_source
, cp_display
);
314 for (i
= 128; i
<= 255; ++i
)
315 conv_displ
[i
] = translate_character (cd
, i
);
319 /* inpit <- display table */
321 cd
= g_iconv_open (cp_source
, cp_display
);
322 if (cd
== INVALID_CONV
)
323 return g_strdup_printf (_("Cannot translate from %s to %s"), cp_display
, cp_source
);
325 for (i
= 128; i
<= 255; ++i
)
328 ch
= translate_character (cd
, i
);
329 conv_input
[i
] = (ch
== UNKNCHAR
) ? i
: ch
;
337 /* --------------------------------------------------------------------------------------------- */
340 convert_to_display (char *str
)
347 *str
= conv_displ
[(unsigned char) *str
];
352 /* --------------------------------------------------------------------------------------------- */
355 str_convert_to_display (const char *str
)
357 return str_nconvert_to_display (str
, -1);
361 /* --------------------------------------------------------------------------------------------- */
364 str_nconvert_to_display (const char *str
, int len
)
370 return g_string_new ("");
372 if (cp_display
== cp_source
)
373 return g_string_new (str
);
375 conv
= str_crt_conv_from (cp_source
);
377 buff
= g_string_new ("");
378 str_nconvert (conv
, str
, len
, buff
);
379 str_close_conv (conv
);
383 /* --------------------------------------------------------------------------------------------- */
386 convert_from_input (char *str
)
393 *str
= conv_input
[(unsigned char) *str
];
398 /* --------------------------------------------------------------------------------------------- */
401 str_convert_to_input (const char *str
)
403 return str_nconvert_to_input (str
, -1);
406 /* --------------------------------------------------------------------------------------------- */
409 str_nconvert_to_input (const char *str
, int len
)
415 return g_string_new ("");
417 if (cp_display
== cp_source
)
418 return g_string_new (str
);
420 conv
= str_crt_conv_to (cp_source
);
422 buff
= g_string_new ("");
423 str_nconvert (conv
, str
, len
, buff
);
424 str_close_conv (conv
);
428 /* --------------------------------------------------------------------------------------------- */
431 convert_from_utf_to_current (const char *str
)
433 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
434 unsigned char ch
= '.';
441 cp_to
= get_codepage_id (mc_global
.source_codepage
);
442 conv
= str_crt_conv_to (cp_to
);
444 if (conv
!= INVALID_CONV
)
446 switch (str_translate_char (conv
, str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
458 str_close_conv (conv
);
464 /* --------------------------------------------------------------------------------------------- */
467 convert_from_utf_to_current_c (int input_char
, GIConv conv
)
469 unsigned char str
[UTF8_CHAR_LEN
+ 1];
470 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
471 unsigned char ch
= '.';
474 res
= g_unichar_to_utf8 (input_char
, (char *) str
);
480 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
496 /* --------------------------------------------------------------------------------------------- */
499 convert_from_8bit_to_utf_c (char input_char
, GIConv conv
)
501 unsigned char str
[2];
502 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
505 str
[0] = (unsigned char) input_char
;
508 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
514 res
= g_utf8_get_char_validated ((char *) buf_ch
, -1);
515 ch
= res
>= 0 ? res
: buf_ch
[0];
528 /* --------------------------------------------------------------------------------------------- */
531 convert_from_8bit_to_utf_c2 (char input_char
)
533 unsigned char str
[2];
538 str
[0] = (unsigned char) input_char
;
541 cp_from
= get_codepage_id (mc_global
.source_codepage
);
542 conv
= str_crt_conv_to (cp_from
);
544 if (conv
!= INVALID_CONV
)
546 unsigned char buf_ch
[UTF8_CHAR_LEN
+ 1];
548 switch (str_translate_char (conv
, (char *) str
, -1, (char *) buf_ch
, sizeof (buf_ch
)))
554 res
= g_utf8_get_char_validated ((char *) buf_ch
, -1);
555 ch
= res
>= 0 ? res
: buf_ch
[0];
564 str_close_conv (conv
);
570 /* --------------------------------------------------------------------------------------------- */