2 * encodings.c - this file is part of Geany, a fast and lightweight IDE
4 * Copyright 2005-2011 Enrico Tröger <enrico(dot)troeger(at)uvena(dot)de>
5 * Copyright 2006-2011 Nick Treleaven <nick(dot)treleaven(at)btinternet(dot)com>
7 * This program is free software; you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation; either version 2 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with this program; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
23 * Encoding conversion and Byte Order Mark (BOM) handling.
27 * Modified by the gedit Team, 2002. See the gedit AUTHORS file for a
28 * list of people on the gedit Team.
29 * See the gedit ChangeLog files for a list of changes.
31 /* Stolen from anjuta */
39 #include "documentprivate.h"
40 #include "msgwindow.h"
41 #include "encodings.h"
42 #include "callbacks.h"
48 # include "gnuregex.h"
51 /* <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> */
52 #define PATTERN_HTMLMETA "<meta[ \t\n\r\f]+http-equiv[ \t\n\r\f]*=[ \t\n\r\f]*\"?content-type\"?[ \t\n\r\f]+content[ \t\n\r\f]*=[ \t\n\r\f]*\"text/x?html;[ \t\n\r\f]*charset=([a-z0-9_-]+)\"[ \t\n\r\f]*/?>"
53 /* " geany_encoding=utf-8 " or " coding: utf-8 " */
54 #define PATTERN_CODING "coding[\t ]*[:=][\t ]*\"?([a-z0-9-]+)\"?[\t ]*"
56 /* precompiled regexps */
57 static regex_t pregs
[2];
58 static gboolean pregs_loaded
= FALSE
;
61 GeanyEncoding encodings
[GEANY_ENCODINGS_MAX
];
64 #define fill(Order, Group, Idx, Charset, Name) \
65 encodings[Idx].idx = Idx; \
66 encodings[Idx].order = Order; \
67 encodings[Idx].group = Group; \
68 encodings[Idx].charset = Charset; \
69 encodings[Idx].name = Name;
71 static void init_encodings(void)
73 fill(0, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_14
, "ISO-8859-14", _("Celtic"));
74 fill(1, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_7
, "ISO-8859-7", _("Greek"));
75 fill(2, WESTEUROPEAN
, GEANY_ENCODING_WINDOWS_1253
, "WINDOWS-1253", _("Greek"));
76 fill(3, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_10
, "ISO-8859-10", _("Nordic"));
77 fill(4, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_3
, "ISO-8859-3", _("South European"));
78 fill(5, WESTEUROPEAN
, GEANY_ENCODING_IBM_850
, "IBM850", _("Western"));
79 fill(6, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_1
, "ISO-8859-1", _("Western"));
80 fill(7, WESTEUROPEAN
, GEANY_ENCODING_ISO_8859_15
, "ISO-8859-15", _("Western"));
81 fill(8, WESTEUROPEAN
, GEANY_ENCODING_WINDOWS_1252
, "WINDOWS-1252", _("Western"));
83 fill(0, EASTEUROPEAN
, GEANY_ENCODING_ISO_8859_4
, "ISO-8859-4", _("Baltic"));
84 fill(1, EASTEUROPEAN
, GEANY_ENCODING_ISO_8859_13
, "ISO-8859-13", _("Baltic"));
85 fill(2, EASTEUROPEAN
, GEANY_ENCODING_WINDOWS_1257
, "WINDOWS-1257", _("Baltic"));
86 fill(3, EASTEUROPEAN
, GEANY_ENCODING_IBM_852
, "IBM852", _("Central European"));
87 fill(4, EASTEUROPEAN
, GEANY_ENCODING_ISO_8859_2
, "ISO-8859-2", _("Central European"));
88 fill(5, EASTEUROPEAN
, GEANY_ENCODING_WINDOWS_1250
, "WINDOWS-1250", _("Central European"));
89 fill(6, EASTEUROPEAN
, GEANY_ENCODING_IBM_855
, "IBM855", _("Cyrillic"));
90 fill(7, EASTEUROPEAN
, GEANY_ENCODING_ISO_8859_5
, "ISO-8859-5", _("Cyrillic"));
91 /* ISO-IR-111 not available on Windows */
92 fill(8, EASTEUROPEAN
, GEANY_ENCODING_ISO_IR_111
, "ISO-IR-111", _("Cyrillic"));
93 fill(9, EASTEUROPEAN
, GEANY_ENCODING_KOI8_R
, "KOI8-R", _("Cyrillic"));
94 fill(10, EASTEUROPEAN
, GEANY_ENCODING_WINDOWS_1251
, "WINDOWS-1251", _("Cyrillic"));
95 fill(11, EASTEUROPEAN
, GEANY_ENCODING_CP_866
, "CP866", _("Cyrillic/Russian"));
96 fill(12, EASTEUROPEAN
, GEANY_ENCODING_KOI8_U
, "KOI8-U", _("Cyrillic/Ukrainian"));
97 fill(13, EASTEUROPEAN
, GEANY_ENCODING_ISO_8859_16
, "ISO-8859-16", _("Romanian"));
99 fill(0, MIDDLEEASTERN
, GEANY_ENCODING_IBM_864
, "IBM864", _("Arabic"));
100 fill(1, MIDDLEEASTERN
, GEANY_ENCODING_ISO_8859_6
, "ISO-8859-6", _("Arabic"));
101 fill(2, MIDDLEEASTERN
, GEANY_ENCODING_WINDOWS_1256
, "WINDOWS-1256", _("Arabic"));
102 fill(3, MIDDLEEASTERN
, GEANY_ENCODING_IBM_862
, "IBM862", _("Hebrew"));
103 /* not available at all, ? */
104 fill(4, MIDDLEEASTERN
, GEANY_ENCODING_ISO_8859_8_I
, "ISO-8859-8-I", _("Hebrew"));
105 fill(5, MIDDLEEASTERN
, GEANY_ENCODING_WINDOWS_1255
, "WINDOWS-1255", _("Hebrew"));
106 fill(6, MIDDLEEASTERN
, GEANY_ENCODING_ISO_8859_8
, "ISO-8859-8", _("Hebrew Visual"));
108 fill(0, ASIAN
, GEANY_ENCODING_ARMSCII_8
, "ARMSCII-8", _("Armenian"));
109 fill(1, ASIAN
, GEANY_ENCODING_GEOSTD8
, "GEORGIAN-ACADEMY", _("Georgian"));
110 fill(2, ASIAN
, GEANY_ENCODING_TIS_620
, "TIS-620", _("Thai"));
111 fill(3, ASIAN
, GEANY_ENCODING_IBM_857
, "IBM857", _("Turkish"));
112 fill(4, ASIAN
, GEANY_ENCODING_WINDOWS_1254
, "WINDOWS-1254", _("Turkish"));
113 fill(5, ASIAN
, GEANY_ENCODING_ISO_8859_9
, "ISO-8859-9", _("Turkish"));
114 fill(6, ASIAN
, GEANY_ENCODING_TCVN
, "TCVN", _("Vietnamese"));
115 fill(7, ASIAN
, GEANY_ENCODING_VISCII
, "VISCII", _("Vietnamese"));
116 fill(8, ASIAN
, GEANY_ENCODING_WINDOWS_1258
, "WINDOWS-1258", _("Vietnamese"));
118 fill(0, UNICODE
, GEANY_ENCODING_UTF_7
, "UTF-7", _("Unicode"));
119 fill(1, UNICODE
, GEANY_ENCODING_UTF_8
, "UTF-8", _("Unicode"));
120 fill(2, UNICODE
, GEANY_ENCODING_UTF_16LE
, "UTF-16LE", _("Unicode"));
121 fill(3, UNICODE
, GEANY_ENCODING_UTF_16BE
, "UTF-16BE", _("Unicode"));
122 fill(4, UNICODE
, GEANY_ENCODING_UCS_2LE
, "UCS-2LE", _("Unicode"));
123 fill(5, UNICODE
, GEANY_ENCODING_UCS_2BE
, "UCS-2BE", _("Unicode"));
124 fill(6, UNICODE
, GEANY_ENCODING_UTF_32LE
, "UTF-32LE", _("Unicode"));
125 fill(7, UNICODE
, GEANY_ENCODING_UTF_32BE
, "UTF-32BE", _("Unicode"));
127 fill(0, EASTASIAN
, GEANY_ENCODING_GB18030
, "GB18030", _("Chinese Simplified"));
128 fill(1, EASTASIAN
, GEANY_ENCODING_GB2312
, "GB2312", _("Chinese Simplified"));
129 fill(2, EASTASIAN
, GEANY_ENCODING_GBK
, "GBK", _("Chinese Simplified"));
130 /* maybe not available on Linux */
131 fill(3, EASTASIAN
, GEANY_ENCODING_HZ
, "HZ", _("Chinese Simplified"));
132 fill(4, EASTASIAN
, GEANY_ENCODING_BIG5
, "BIG5", _("Chinese Traditional"));
133 fill(5, EASTASIAN
, GEANY_ENCODING_BIG5_HKSCS
, "BIG5-HKSCS", _("Chinese Traditional"));
134 fill(6, EASTASIAN
, GEANY_ENCODING_EUC_TW
, "EUC-TW", _("Chinese Traditional"));
135 fill(7, EASTASIAN
, GEANY_ENCODING_EUC_JP
, "EUC-JP", _("Japanese"));
136 fill(8, EASTASIAN
, GEANY_ENCODING_ISO_2022_JP
, "ISO-2022-JP", _("Japanese"));
137 fill(9, EASTASIAN
, GEANY_ENCODING_SHIFT_JIS
, "SHIFT_JIS", _("Japanese"));
138 fill(10, EASTASIAN
, GEANY_ENCODING_CP_932
, "CP932", _("Japanese"));
139 fill(11, EASTASIAN
, GEANY_ENCODING_EUC_KR
, "EUC-KR", _("Korean"));
140 fill(12, EASTASIAN
, GEANY_ENCODING_ISO_2022_KR
, "ISO-2022-KR", _("Korean"));
141 fill(13, EASTASIAN
, GEANY_ENCODING_JOHAB
, "JOHAB", _("Korean"));
142 fill(14, EASTASIAN
, GEANY_ENCODING_UHC
, "UHC", _("Korean"));
144 fill(0, NONE
, GEANY_ENCODING_NONE
, "None", _("Without encoding"));
148 /* compares two encoding names in a permissive fashion.
149 * e.g. "utf8" matches "UTF-8", "iso8859_1" matches "ISO-8859-1", etc. */
150 static gboolean
encodings_charset_equals(const gchar
*a
, const gchar
*b
)
152 gboolean was_alpha
= FALSE
; /* whether last character of previous word was a letter */
153 gboolean need_sep
= FALSE
; /* whether we're expecting an implicit separator */
159 if (g_ascii_toupper(*a
) == g_ascii_toupper(*b
) &&
160 ((is_alpha
= g_ascii_isalpha(*a
)) || g_ascii_isdigit(*a
)))
162 /* either there was a real separator, or we need a implicit one (a chage from alpha to
164 if (! need_sep
|| (was_alpha
!= is_alpha
))
168 was_alpha
= is_alpha
;
178 if (! g_ascii_isalnum(*a
))
183 if (! g_ascii_isalnum(*b
))
198 GeanyEncodingIndex
encodings_get_idx_from_charset(const gchar
*charset
)
203 return GEANY_ENCODING_UTF_8
;
206 while (i
< GEANY_ENCODINGS_MAX
)
208 if (encodings_charset_equals(charset
, encodings
[i
].charset
))
213 return GEANY_ENCODING_UTF_8
;
217 const GeanyEncoding
*encodings_get_from_charset(const gchar
*charset
)
222 return &encodings
[GEANY_ENCODING_UTF_8
];
225 while (i
< GEANY_ENCODINGS_MAX
)
227 if (encodings_charset_equals(charset
, encodings
[i
].charset
))
228 return &encodings
[i
];
237 static const gchar
*encodings_normalize_charset(const gchar
*charset
)
239 const GeanyEncoding
*encoding
;
241 encoding
= encodings_get_from_charset(charset
);
242 if (encoding
!= NULL
)
243 return encoding
->charset
;
249 const GeanyEncoding
*encodings_get_from_index(gint idx
)
251 g_return_val_if_fail(idx
>= 0 && idx
< GEANY_ENCODINGS_MAX
, NULL
);
253 return &encodings
[idx
];
258 * Gets the character set name of the specified index e.g. for use with
259 * @ref document_set_encoding().
261 * @param idx @ref GeanyEncodingIndex to retrieve the corresponding character set.
264 * @return The charset according to idx, or @c NULL if the index is invalid.
268 const gchar
* encodings_get_charset_from_index(gint idx
)
270 g_return_val_if_fail(idx
>= 0 && idx
< GEANY_ENCODINGS_MAX
, NULL
);
272 return encodings
[idx
].charset
;
276 gchar
*encodings_to_string(const GeanyEncoding
* enc
)
278 g_return_val_if_fail(enc
!= NULL
, NULL
);
279 g_return_val_if_fail(enc
->name
!= NULL
, NULL
);
280 g_return_val_if_fail(enc
->charset
!= NULL
, NULL
);
282 return g_strdup_printf("%s (%s)", enc
->name
, enc
->charset
);
286 const gchar
*encodings_get_charset(const GeanyEncoding
* enc
)
288 g_return_val_if_fail(enc
!= NULL
, NULL
);
289 g_return_val_if_fail(enc
->charset
!= NULL
, NULL
);
295 static GtkWidget
*radio_items
[GEANY_ENCODINGS_MAX
];
298 void encodings_select_radio_item(const gchar
*charset
)
302 g_return_if_fail(charset
!= NULL
);
305 while (i
< GEANY_ENCODINGS_MAX
)
307 if (utils_str_equal(charset
, encodings
[i
].charset
))
311 if (i
== GEANY_ENCODINGS_MAX
)
312 i
= GEANY_ENCODING_UTF_8
; /* fallback to UTF-8 */
314 /* ignore_callback has to be set by the caller */
315 gtk_check_menu_item_set_active(GTK_CHECK_MENU_ITEM(radio_items
[i
]), TRUE
);
319 /* Regexp detection of file encoding declared in the file itself.
320 * Idea and parts of code taken from Bluefish, thanks.
321 * regex_compile() is used to compile regular expressions on program init and keep it in memory
322 * for faster access when opening a file. Pre-compiled regexps will be freed on program exit.
324 static void regex_compile(regex_t
*preg
, const gchar
*pattern
)
326 gint retval
= regcomp(preg
, pattern
, REG_EXTENDED
| REG_ICASE
);
330 regerror(retval
, preg
, errmsg
, 512);
331 geany_debug("regcomp() failed (%s)", errmsg
);
338 static gchar
*regex_match(regex_t
*preg
, const gchar
*buffer
, gsize size
)
341 gchar
*tmp_buf
= NULL
;
342 gchar
*encoding
= NULL
;
343 regmatch_t pmatch
[10];
345 if (G_UNLIKELY(! pregs_loaded
|| buffer
== NULL
))
349 tmp_buf
= g_strndup(buffer
, 512); /* scan only the first 512 characters in the buffer */
351 retval
= regexec(preg
, (tmp_buf
!= NULL
) ? tmp_buf
: buffer
, 10, pmatch
, 0);
352 if (retval
== 0 && pmatch
[0].rm_so
!= -1 && pmatch
[1].rm_so
!= -1)
354 encoding
= g_strndup(&buffer
[pmatch
[1].rm_so
], pmatch
[1].rm_eo
- pmatch
[1].rm_so
);
355 geany_debug("Detected encoding by regex search: %s", encoding
);
357 setptr(encoding
, g_utf8_strup(encoding
, -1));
364 static void encodings_radio_item_change_cb(GtkCheckMenuItem
*menuitem
, gpointer user_data
)
366 GeanyDocument
*doc
= document_get_current();
367 guint i
= GPOINTER_TO_INT(user_data
);
369 if (ignore_callback
|| doc
== NULL
|| encodings
[i
].charset
== NULL
||
370 ! gtk_check_menu_item_get_active(menuitem
) ||
371 utils_str_equal(encodings
[i
].charset
, doc
->encoding
))
379 document_undo_add(doc
, UNDO_ENCODING
, g_strdup(doc
->encoding
));
381 document_set_encoding(doc
, encodings
[i
].charset
);
385 void encodings_finalize(void)
390 len
= G_N_ELEMENTS(pregs
);
391 for (i
= 0; i
< len
; i
++)
399 void encodings_init(void)
401 GtkWidget
*item
, *menu
[2], *submenu
, *menu_westeuro
, *menu_easteuro
, *menu_eastasian
, *menu_asian
,
402 *menu_utf8
, *menu_middleeast
, *item_westeuro
, *item_easteuro
, *item_eastasian
,
403 *item_asian
, *item_utf8
, *item_middleeast
;
404 GCallback cb_func
[2];
405 GSList
*group
= NULL
;
407 gint order
, group_size
;
414 regex_compile(&pregs
[0], PATTERN_HTMLMETA
);
415 regex_compile(&pregs
[1], PATTERN_CODING
);
419 /* create encodings submenu in document menu */
420 menu
[0] = ui_lookup_widget(main_widgets
.window
, "set_encoding1_menu");
421 menu
[1] = ui_lookup_widget(main_widgets
.window
, "menu_reload_as1_menu");
422 cb_func
[0] = G_CALLBACK(encodings_radio_item_change_cb
);
423 cb_func
[1] = G_CALLBACK(on_reload_as_activate
);
425 for (k
= 0; k
< 2; k
++)
427 menu_westeuro
= gtk_menu_new();
428 item_westeuro
= gtk_menu_item_new_with_mnemonic(_("_West European"));
429 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_westeuro
), menu_westeuro
);
430 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_westeuro
);
431 gtk_widget_show_all(item_westeuro
);
433 menu_easteuro
= gtk_menu_new();
434 item_easteuro
= gtk_menu_item_new_with_mnemonic(_("_East European"));
435 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_easteuro
), menu_easteuro
);
436 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_easteuro
);
437 gtk_widget_show_all(item_easteuro
);
439 menu_eastasian
= gtk_menu_new();
440 item_eastasian
= gtk_menu_item_new_with_mnemonic(_("East _Asian"));
441 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_eastasian
), menu_eastasian
);
442 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_eastasian
);
443 gtk_widget_show_all(item_eastasian
);
445 menu_asian
= gtk_menu_new();
446 item_asian
= gtk_menu_item_new_with_mnemonic(_("_SE & SW Asian"));
447 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_asian
), menu_asian
);
448 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_asian
);
449 gtk_widget_show_all(item_asian
);
451 menu_middleeast
= gtk_menu_new();
452 item_middleeast
= gtk_menu_item_new_with_mnemonic(_("_Middle Eastern"));
453 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_middleeast
), menu_middleeast
);
454 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_middleeast
);
455 gtk_widget_show_all(item_middleeast
);
457 menu_utf8
= gtk_menu_new();
458 item_utf8
= gtk_menu_item_new_with_mnemonic(_("_Unicode"));
459 gtk_menu_item_set_submenu(GTK_MENU_ITEM(item_utf8
), menu_utf8
);
460 gtk_container_add(GTK_CONTAINER(menu
[k
]), item_utf8
);
461 gtk_widget_show_all(item_utf8
);
463 /** TODO can it be optimized? ATM 3782 runs at line "if (encodings[j].group ...)" */
464 for (i
= 0; i
< GEANY_ENCODING_GROUPS_MAX
; i
++)
469 case WESTEUROPEAN
: submenu
= menu_westeuro
; group_size
= 9; break;
470 case EASTEUROPEAN
: submenu
= menu_easteuro
; group_size
= 14; break;
471 case EASTASIAN
: submenu
= menu_eastasian
; group_size
= 14; break;
472 case ASIAN
: submenu
= menu_asian
; group_size
= 9; break;
473 case MIDDLEEASTERN
: submenu
= menu_middleeast
; group_size
= 7; break;
474 case UNICODE
: submenu
= menu_utf8
; group_size
= 8; break;
475 default: submenu
= menu
[k
]; group_size
= 1;
478 while (order
< group_size
) /* the biggest group has 13 elements */
480 for (j
= 0; j
< GEANY_ENCODINGS_MAX
; j
++)
482 if (encodings
[j
].group
== i
&& encodings
[j
].order
== order
)
484 label
= encodings_to_string(&encodings
[j
]);
487 item
= gtk_radio_menu_item_new_with_label(group
, label
);
488 group
= gtk_radio_menu_item_get_group(GTK_RADIO_MENU_ITEM(item
));
489 radio_items
[j
] = item
;
492 item
= gtk_menu_item_new_with_label(label
);
493 gtk_widget_show(item
);
494 gtk_container_add(GTK_CONTAINER(submenu
), item
);
495 g_signal_connect(item
, "activate",
496 cb_func
[k
], GINT_TO_POINTER(encodings
[j
].idx
));
509 * Tries to convert @a buffer into UTF-8 encoding from the encoding specified with @a charset.
510 * If @a fast is not set, additional checks to validate the converted string are performed.
512 * @param buffer The input string to convert.
513 * @param size The length of the string, or -1 if the string is nul-terminated.
514 * @param charset The charset to be used for conversion.
515 * @param fast @c TRUE to only convert the input and skip extended checks on the converted string.
517 * @return If the conversion was successful, a newly allocated nul-terminated string,
518 * which must be freed with @c g_free(). Otherwise @c NULL.
520 gchar
*encodings_convert_to_utf8_from_charset(const gchar
*buffer
, gsize size
,
521 const gchar
*charset
, gboolean fast
)
523 gchar
*utf8_content
= NULL
;
524 GError
*conv_error
= NULL
;
525 gchar
* converted_contents
= NULL
;
528 g_return_val_if_fail(buffer
!= NULL
, NULL
);
529 g_return_val_if_fail(charset
!= NULL
, NULL
);
531 converted_contents
= g_convert(buffer
, size
, "UTF-8", charset
, NULL
,
532 &bytes_written
, &conv_error
);
536 utf8_content
= converted_contents
;
537 if (conv_error
!= NULL
) g_error_free(conv_error
);
539 else if (conv_error
!= NULL
|| ! g_utf8_validate(converted_contents
, bytes_written
, NULL
))
541 if (conv_error
!= NULL
)
543 geany_debug("Couldn't convert from %s to UTF-8 (%s).", charset
, conv_error
->message
);
544 g_error_free(conv_error
);
548 geany_debug("Couldn't convert from %s to UTF-8.", charset
);
551 g_free(converted_contents
);
555 geany_debug("Converted from %s to UTF-8.", charset
);
556 utf8_content
= converted_contents
;
563 static gchar
*encodings_check_regexes(const gchar
*buffer
, gsize size
)
567 for (i
= 0; i
< G_N_ELEMENTS(pregs
); i
++)
571 if ((charset
= regex_match(&pregs
[i
], buffer
, size
)) != NULL
)
578 static gchar
*encodings_convert_to_utf8_with_suggestion(const gchar
*buffer
, gsize size
,
579 const gchar
*suggested_charset
, gchar
**used_encoding
)
581 const gchar
*locale_charset
= NULL
;
582 const gchar
*charset
;
584 gboolean check_suggestion
= suggested_charset
!= NULL
;
585 gboolean check_locale
= FALSE
;
586 gint i
, preferred_charset
;
588 if ((gint
)size
== -1)
590 size
= strlen(buffer
);
593 /* current locale is not UTF-8, we have to check this charset */
594 check_locale
= ! g_get_charset(&locale_charset
);
596 /* First check for preferred charset, if specified */
597 preferred_charset
= file_prefs
.default_open_encoding
;
599 if (preferred_charset
== encodings
[GEANY_ENCODING_NONE
].idx
||
600 preferred_charset
< 0 ||
601 preferred_charset
>= GEANY_ENCODINGS_MAX
)
603 preferred_charset
= -1;
606 /* -1 means "Preferred charset" */
607 for (i
= -1; i
< GEANY_ENCODINGS_MAX
; i
++)
609 if (G_UNLIKELY(i
== encodings
[GEANY_ENCODING_NONE
].idx
))
612 if (check_suggestion
)
614 check_suggestion
= FALSE
;
615 charset
= encodings_normalize_charset(suggested_charset
);
616 if (charset
== NULL
) /* we failed at normalizing suggested encoding, try it as is */
617 charset
= suggested_charset
;
618 i
= -2; /* keep i below the start value to have it again at -1 on the next loop run */
620 else if (check_locale
)
622 check_locale
= FALSE
;
623 charset
= locale_charset
;
624 i
= -2; /* keep i below the start value to have it again at -1 on the next loop run */
628 if (preferred_charset
>= 0)
630 charset
= encodings
[preferred_charset
].charset
;
631 geany_debug("Using preferred charset: %s", charset
);
637 charset
= encodings
[i
].charset
;
638 else /* in this case we have i == -2, continue to increase i and go ahead */
641 if (G_UNLIKELY(charset
== NULL
))
644 geany_debug("Trying to convert %" G_GSIZE_FORMAT
" bytes of data from %s into UTF-8.",
646 utf8_content
= encodings_convert_to_utf8_from_charset(buffer
, size
, charset
, FALSE
);
648 if (G_LIKELY(utf8_content
!= NULL
))
650 if (used_encoding
!= NULL
)
652 if (G_UNLIKELY(*used_encoding
!= NULL
))
654 geany_debug("%s:%d", __FILE__
, __LINE__
);
655 g_free(*used_encoding
);
657 *used_encoding
= g_strdup(charset
);
668 * Tries to convert @a buffer into UTF-8 encoding and store the detected original encoding in
671 * @param buffer the input string to convert.
672 * @param size the length of the string, or -1 if the string is nul-terminated.
673 * @param used_encoding return location of the detected encoding of the input string, or @c NULL.
675 * @return If the conversion was successful, a newly allocated nul-terminated string,
676 * which must be freed with @c g_free(). Otherwise @c NULL.
678 gchar
*encodings_convert_to_utf8(const gchar
*buffer
, gsize size
, gchar
**used_encoding
)
680 gchar
*regex_charset
;
683 /* first try to read the encoding from the file content */
684 regex_charset
= encodings_check_regexes(buffer
, size
);
685 utf8
= encodings_convert_to_utf8_with_suggestion(buffer
, size
, regex_charset
, used_encoding
);
686 g_free(regex_charset
);
692 /* If there's a BOM, return a corresponding GEANY_ENCODING_UTF_* index,
693 * otherwise GEANY_ENCODING_NONE.
695 GeanyEncodingIndex
encodings_scan_unicode_bom(const gchar
*string
, gsize len
, guint
*bom_len
)
702 if ((guchar
)string
[0] == 0xef && (guchar
)string
[1] == 0xbb &&
703 (guchar
)string
[2] == 0xbf)
705 return GEANY_ENCODING_UTF_8
;
713 if ((guchar
)string
[0] == 0x00 && (guchar
)string
[1] == 0x00 &&
714 (guchar
)string
[2] == 0xfe && (guchar
)string
[3] == 0xff)
716 return GEANY_ENCODING_UTF_32BE
; /* Big endian */
718 if ((guchar
)string
[0] == 0xff && (guchar
)string
[1] == 0xfe &&
719 (guchar
)string
[2] == 0x00 && (guchar
)string
[3] == 0x00)
721 return GEANY_ENCODING_UTF_32LE
; /* Little endian */
723 if ((string
[0] == 0x2b && string
[1] == 0x2f && string
[2] == 0x76) &&
724 (string
[3] == 0x38 || string
[3] == 0x39 || string
[3] == 0x2b || string
[3] == 0x2f))
726 return GEANY_ENCODING_UTF_7
;
734 if ((guchar
)string
[0] == 0xfe && (guchar
)string
[1] == 0xff)
736 return GEANY_ENCODING_UTF_16BE
; /* Big endian */
738 if ((guchar
)string
[0] == 0xff && (guchar
)string
[1] == 0xfe)
740 return GEANY_ENCODING_UTF_16LE
; /* Little endian */
745 return GEANY_ENCODING_NONE
;
749 gboolean
encodings_is_unicode_charset(const gchar
*string
)
751 if (string
!= NULL
&&
752 (strncmp(string
, "UTF", 3) == 0 || strncmp(string
, "UCS", 3) == 0))
762 gchar
*data
; /* null-terminated data */
763 gsize size
; /* actual data size */
764 gsize len
; /* string length of data */
771 /* convert data with the specified encoding */
773 handle_forced_encoding(BufferData
*buffer
, const gchar
*forced_enc
)
775 GeanyEncodingIndex enc_idx
;
777 if (utils_str_equal(forced_enc
, "UTF-8"))
779 if (! g_utf8_validate(buffer
->data
, buffer
->len
, NULL
))
786 gchar
*converted_text
= encodings_convert_to_utf8_from_charset(
787 buffer
->data
, buffer
->size
, forced_enc
, FALSE
);
788 if (converted_text
== NULL
)
794 setptr(buffer
->data
, converted_text
);
795 buffer
->len
= strlen(converted_text
);
798 enc_idx
= encodings_scan_unicode_bom(buffer
->data
, buffer
->size
, NULL
);
799 buffer
->bom
= (enc_idx
== GEANY_ENCODING_UTF_8
);
800 buffer
->enc
= g_strdup(forced_enc
);
805 /* detect encoding and convert to UTF-8 if necessary */
807 handle_encoding(BufferData
*buffer
, GeanyEncodingIndex enc_idx
)
809 g_return_val_if_fail(buffer
->enc
== NULL
, FALSE
);
810 g_return_val_if_fail(buffer
->bom
== FALSE
, FALSE
);
812 if (buffer
->size
== 0)
814 /* we have no data so assume UTF-8, buffer->len can be 0 even we have an empty
815 * e.g. UTF32 file with a BOM(so size is 4, len is 0) */
816 buffer
->enc
= g_strdup("UTF-8");
820 /* first check for a BOM */
821 if (enc_idx
!= GEANY_ENCODING_NONE
)
823 buffer
->enc
= g_strdup(encodings
[enc_idx
].charset
);
826 if (enc_idx
!= GEANY_ENCODING_UTF_8
) /* the BOM indicated something else than UTF-8 */
828 gchar
*converted_text
= encodings_convert_to_utf8_from_charset(
829 buffer
->data
, buffer
->size
, buffer
->enc
, FALSE
);
830 if (converted_text
!= NULL
)
832 setptr(buffer
->data
, converted_text
);
833 buffer
->len
= strlen(converted_text
);
837 /* there was a problem converting data from BOM encoding type */
838 setptr(buffer
->enc
, NULL
);
844 if (buffer
->enc
== NULL
) /* either there was no BOM or the BOM encoding failed */
846 /* first try to read the encoding from the file content */
847 gchar
*regex_charset
= encodings_check_regexes(buffer
->data
, buffer
->size
);
849 /* try UTF-8 first */
850 if (encodings_get_idx_from_charset(regex_charset
) == GEANY_ENCODING_UTF_8
&&
851 (buffer
->size
== buffer
->len
) && g_utf8_validate(buffer
->data
, buffer
->len
, NULL
))
853 buffer
->enc
= g_strdup("UTF-8");
857 /* detect the encoding */
858 gchar
*converted_text
= encodings_convert_to_utf8_with_suggestion(buffer
->data
,
859 buffer
->size
, regex_charset
, &buffer
->enc
);
861 if (converted_text
== NULL
)
863 g_free(regex_charset
);
866 setptr(buffer
->data
, converted_text
);
867 buffer
->len
= strlen(converted_text
);
869 g_free(regex_charset
);
877 handle_bom(BufferData
*buffer
)
881 encodings_scan_unicode_bom(buffer
->data
, buffer
->size
, &bom_len
);
882 g_return_if_fail(bom_len
!= 0);
884 /* use filedata->len here because the contents are already converted into UTF-8 */
885 buffer
->len
-= bom_len
;
886 /* overwrite the BOM with the remainder of the file contents, plus the NULL terminator. */
887 g_memmove(buffer
->data
, buffer
->data
+ bom_len
, buffer
->len
+ 1);
888 buffer
->data
= g_realloc(buffer
->data
, buffer
->len
+ 1);
892 /* loads textfile data, verifies and converts to forced_enc or UTF-8. Also handles BOM. */
893 static gboolean
handle_buffer(BufferData
*buffer
, const gchar
*forced_enc
)
895 GeanyEncodingIndex tmp_enc_idx
;
897 /* temporarily retrieve the encoding idx based on the BOM to suppress the following warning
898 * if we have a BOM */
899 tmp_enc_idx
= encodings_scan_unicode_bom(buffer
->data
, buffer
->size
, NULL
);
901 /* check whether the size of the loaded data is equal to the size of the file in the
902 * filesystem file size may be 0 to allow opening files in /proc/ which have typically a
903 * file size of 0 bytes */
904 if (buffer
->len
!= buffer
->size
&& buffer
->size
!= 0 && (
905 tmp_enc_idx
== GEANY_ENCODING_UTF_8
|| /* tmp_enc_idx can be UTF-7/8/16/32, UCS and None */
906 tmp_enc_idx
== GEANY_ENCODING_UTF_7
)) /* filter UTF-7/8 where no NULL bytes are allowed */
908 buffer
->partial
= TRUE
;
911 /* Determine character encoding and convert to UTF-8 */
912 if (forced_enc
!= NULL
)
914 /* the encoding should be ignored(requested by user), so open the file "as it is" */
915 if (utils_str_equal(forced_enc
, encodings
[GEANY_ENCODING_NONE
].charset
))
918 buffer
->enc
= g_strdup(encodings
[GEANY_ENCODING_NONE
].charset
);
920 else if (! handle_forced_encoding(buffer
, forced_enc
))
925 else if (! handle_encoding(buffer
, tmp_enc_idx
))
937 * Tries to convert @a buffer into UTF-8 encoding. Unlike encodings_convert_to_utf8()
938 * and encodings_convert_to_utf8_from_charset() it handles the possible BOM in the data.
940 * @param buf a pointer to modifiable null-terminated buffer to convert.
941 * It may or may not be modified, and should be freed whatever happens.
942 * @param size a pointer to the size of the buffer (expected to be e.g. the on-disk
943 * file size). It will be updated to the new size.
944 * @param forced_enc forced encoding to use, or @c NULL
945 * @param used_encoding return location for the actually used encoding, or @c NULL
946 * @param has_bom return location to store whether the data had a BOM, or @c NULL
947 * @param partial return location to store whether the conversion may be partial, or @c NULL
949 * @return @C TRUE if the conversion succeeded, @c FALSE otherwise.
951 gboolean
encodings_convert_to_utf8_auto(gchar
**buf
, gsize
*size
, const gchar
*forced_enc
,
952 gchar
**used_encoding
, gboolean
*has_bom
, gboolean
*partial
)
958 /* use strlen to check for null chars */
959 buffer
.len
= strlen(buffer
.data
);
962 buffer
.partial
= FALSE
;
964 if (! handle_buffer(&buffer
, forced_enc
))
969 *used_encoding
= buffer
.enc
;
973 *has_bom
= buffer
.bom
;
975 *partial
= buffer
.partial
;