2 * Sylpheed -- a GTK+ based, lightweight, and fast e-mail client
3 * Copyright (C) 1999-2007 Hiroyuki Yamamoto and the Claws Mail team
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 3 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, see <http://www.gnu.org/licenses/>.
27 #include <glib/gi18n.h>
40 #include "quoted-printable.h"
42 #include "prefs_common.h"
44 /* For unknown reasons the inconv.m4 macro undefs that macro if no
45 const is needed. This would break the code below so we define it. */
58 #define SUBST_CHAR 0x5f;
61 #define iseuckanji(c) \
62 (((c) & 0xff) >= 0xa1 && ((c) & 0xff) <= 0xfe)
63 #define iseuchwkana1(c) \
64 (((c) & 0xff) == 0x8e)
65 #define iseuchwkana2(c) \
66 (((c) & 0xff) >= 0xa1 && ((c) & 0xff) <= 0xdf)
68 (((c) & 0xff) == 0x8f)
69 #define issjiskanji1(c) \
70 ((((c) & 0xff) >= 0x81 && ((c) & 0xff) <= 0x9f) || \
71 (((c) & 0xff) >= 0xe0 && ((c) & 0xff) <= 0xfc))
72 #define issjiskanji2(c) \
73 ((((c) & 0xff) >= 0x40 && ((c) & 0xff) <= 0x7e) || \
74 (((c) & 0xff) >= 0x80 && ((c) & 0xff) <= 0xfc))
75 #define issjishwkana(c) \
76 (((c) & 0xff) >= 0xa1 && ((c) & 0xff) <= 0xdf)
79 if (state != JIS_KANJI) { \
87 if (state != JIS_ASCII) { \
95 if (state != JIS_HWKANA) { \
103 if (state != JIS_AUXKANJI) { \
108 state = JIS_AUXKANJI; \
111 static CodeConvFunc conv_get_code_conv_func (const gchar *src_charset_str,
112 const gchar *dest_charset_str);
114 static gchar *conv_iconv_strdup_with_cd (const gchar *inbuf,
117 static gchar *conv_iconv_strdup (const gchar *inbuf,
118 const gchar *src_code,
119 const gchar *dest_code);
121 static CharSet conv_get_locale_charset (void);
122 static CharSet conv_get_outgoing_charset (void);
123 static CharSet conv_guess_ja_encoding(const gchar *str);
124 static gboolean conv_is_ja_locale (void);
126 static void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
127 static void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf);
128 static void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
130 static void conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
131 static void conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
132 static void conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
133 static void conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
135 static void conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
136 static void conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf);
138 static void conv_unreadable_8bit(gchar *str);
140 static void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
141 static void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
142 static void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
144 static void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
145 static void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
146 static void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf);
148 static gboolean strict_mode = FALSE;
150 void codeconv_set_strict(gboolean mode)
155 static void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
157 const guchar *in = inbuf;
158 guchar *out = outbuf;
159 JISState state = JIS_ASCII;
161 while (*in != '\0') {
165 if (*(in + 1) == '@' || *(in + 1) == 'B') {
168 } else if (*(in + 1) == '(' &&
170 state = JIS_AUXKANJI;
173 /* unknown escape sequence */
176 } else if (*in == '(') {
177 if (*(in + 1) == 'B' || *(in + 1) == 'J') {
180 } else if (*(in + 1) == 'I') {
184 /* unknown escape sequence */
188 /* unknown escape sequence */
191 } else if (*in == 0x0e) {
194 } else if (*in == 0x0f) {
203 *out++ = *in++ | 0x80;
204 if (*in == '\0') break;
205 *out++ = *in++ | 0x80;
209 *out++ = *in++ | 0x80;
213 *out++ = *in++ | 0x80;
214 if (*in == '\0') break;
215 *out++ = *in++ | 0x80;
224 #define JIS_HWDAKUTEN 0x5e
225 #define JIS_HWHANDAKUTEN 0x5f
227 static gint conv_jis_hantozen(guchar *outbuf, guchar jis_code, guchar sound_sym)
229 static guint16 h2z_tbl[] = {
231 0x0000, 0x2123, 0x2156, 0x2157, 0x2122, 0x2126, 0x2572, 0x2521,
232 0x2523, 0x2525, 0x2527, 0x2529, 0x2563, 0x2565, 0x2567, 0x2543,
234 0x213c, 0x2522, 0x2524, 0x2526, 0x2528, 0x252a, 0x252b, 0x252d,
235 0x252f, 0x2531, 0x2533, 0x2535, 0x2537, 0x2539, 0x253b, 0x253d,
237 0x253f, 0x2541, 0x2544, 0x2546, 0x2548, 0x254a, 0x254b, 0x254c,
238 0x254d, 0x254e, 0x254f, 0x2552, 0x2555, 0x2558, 0x255b, 0x255e,
240 0x255f, 0x2560, 0x2561, 0x2562, 0x2564, 0x2566, 0x2568, 0x2569,
241 0x256a, 0x256b, 0x256c, 0x256d, 0x256f, 0x2573, 0x212b, 0x212c
244 static guint16 dakuten_tbl[] = {
246 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x252c, 0x252e,
247 0x2530, 0x2532, 0x2534, 0x2536, 0x2538, 0x253a, 0x253c, 0x253e,
249 0x2540, 0x2542, 0x2545, 0x2547, 0x2549, 0x0000, 0x0000, 0x0000,
250 0x0000, 0x0000, 0x2550, 0x2553, 0x2556, 0x2559, 0x255c, 0x0000
253 static guint16 handakuten_tbl[] = {
255 0x2551, 0x2554, 0x2557, 0x255a, 0x255d
263 if (jis_code < 0x21 || jis_code > 0x5f)
266 if (sound_sym == JIS_HWDAKUTEN &&
267 jis_code >= 0x36 && jis_code <= 0x4e) {
268 out_code = dakuten_tbl[jis_code - 0x30];
270 *outbuf = out_code >> 8;
271 *(outbuf + 1) = out_code & 0xff;
276 if (sound_sym == JIS_HWHANDAKUTEN &&
277 jis_code >= 0x4a && jis_code <= 0x4e) {
278 out_code = handakuten_tbl[jis_code - 0x4a];
279 *outbuf = out_code >> 8;
280 *(outbuf + 1) = out_code & 0xff;
284 out_code = h2z_tbl[jis_code - 0x20];
285 *outbuf = out_code >> 8;
286 *(outbuf + 1) = out_code & 0xff;
290 static void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
292 const guchar *in = inbuf;
293 guchar *out = outbuf;
294 JISState state = JIS_ASCII;
296 while (*in != '\0') {
300 } else if (iseuckanji(*in)) {
301 if (iseuckanji(*(in + 1))) {
303 *out++ = *in++ & 0x7f;
304 *out++ = *in++ & 0x7f;
309 if (*in != '\0' && !IS_ASCII(*in)) {
314 } else if (iseuchwkana1(*in)) {
315 if (iseuchwkana2(*(in + 1))) {
316 if (prefs_common.allow_jisx0201_kana) {
319 *out++ = *in++ & 0x7f;
324 if (iseuchwkana1(*(in + 2)) &&
325 iseuchwkana2(*(in + 3)))
326 len = conv_jis_hantozen
328 *(in + 1), *(in + 3));
330 len = conv_jis_hantozen
345 if (*in != '\0' && !IS_ASCII(*in)) {
350 } else if (iseucaux(*in)) {
352 if (iseuckanji(*in) && iseuckanji(*(in + 1))) {
354 *out++ = *in++ & 0x7f;
355 *out++ = *in++ & 0x7f;
358 if (*in != '\0' && !IS_ASCII(*in)) {
361 if (*in != '\0' && !IS_ASCII(*in)) {
378 static void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
380 const guchar *in = inbuf;
381 guchar *out = outbuf;
383 while (*in != '\0') {
386 } else if (issjiskanji1(*in)) {
387 if (issjiskanji2(*(in + 1))) {
389 guchar out2 = *(in + 1);
392 row = out1 < 0xa0 ? 0x70 : 0xb0;
394 out1 = (out1 - row) * 2 - 1;
395 out2 -= out2 > 0x7f ? 0x20 : 0x1f;
397 out1 = (out1 - row) * 2;
401 *out++ = out1 | 0x80;
402 *out++ = out2 | 0x80;
407 if (*in != '\0' && !IS_ASCII(*in)) {
412 } else if (issjishwkana(*in)) {
424 static void conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
428 Xalloca(eucstr, outlen, return);
430 conv_jistoeuc(eucstr, outlen, inbuf);
431 conv_euctoutf8(outbuf, outlen, eucstr);
434 static void conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
438 tmpstr = conv_iconv_strdup(inbuf, CS_SHIFT_JIS, CS_UTF_8);
440 strncpy2(outbuf, tmpstr, outlen);
443 strncpy2(outbuf, inbuf, outlen);
446 static void conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
448 static iconv_t cd = (iconv_t)-1;
449 static gboolean iconv_ok = TRUE;
452 if (cd == (iconv_t)-1) {
454 strncpy2(outbuf, inbuf, outlen);
457 cd = iconv_open(CS_UTF_8, CS_EUC_JP_MS);
458 if (cd == (iconv_t)-1) {
459 cd = iconv_open(CS_UTF_8, CS_EUC_JP);
460 if (cd == (iconv_t)-1) {
461 g_warning("conv_euctoutf8(): %s\n",
464 strncpy2(outbuf, inbuf, outlen);
470 tmpstr = conv_iconv_strdup_with_cd(inbuf, cd);
472 strncpy2(outbuf, tmpstr, outlen);
475 strncpy2(outbuf, inbuf, outlen);
478 static void conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
480 switch (conv_guess_ja_encoding(inbuf)) {
482 conv_jistoutf8(outbuf, outlen, inbuf);
485 conv_sjistoutf8(outbuf, outlen, inbuf);
488 conv_euctoutf8(outbuf, outlen, inbuf);
491 strncpy2(outbuf, inbuf, outlen);
496 static void conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
498 static iconv_t cd = (iconv_t)-1;
499 static gboolean iconv_ok = TRUE;
502 if (cd == (iconv_t)-1) {
504 strncpy2(outbuf, inbuf, outlen);
507 cd = iconv_open(CS_EUC_JP_MS, CS_UTF_8);
508 if (cd == (iconv_t)-1) {
509 cd = iconv_open(CS_EUC_JP, CS_UTF_8);
510 if (cd == (iconv_t)-1) {
511 g_warning("conv_utf8toeuc(): %s\n",
514 strncpy2(outbuf, inbuf, outlen);
520 tmpstr = conv_iconv_strdup_with_cd(inbuf, cd);
522 strncpy2(outbuf, tmpstr, outlen);
525 strncpy2(outbuf, inbuf, outlen);
528 static void conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf)
532 Xalloca(eucstr, outlen, return);
534 conv_utf8toeuc(eucstr, outlen, inbuf);
535 conv_euctojis(outbuf, outlen, eucstr);
538 static void conv_unreadable_8bit(gchar *str)
540 register guchar *p = str;
543 /* convert CR+LF -> LF */
544 if (*p == '\r' && *(p + 1) == '\n')
545 memmove(p, p + 1, strlen(p));
546 else if (!IS_ASCII(*p)) *p = SUBST_CHAR;
551 static CharSet conv_guess_ja_encoding(const gchar *str)
553 const guchar *p = str;
554 CharSet guessed = C_US_ASCII;
557 if (*p == ESC && (*(p + 1) == '$' || *(p + 1) == '(')) {
558 if (guessed == C_US_ASCII)
559 return C_ISO_2022_JP;
561 } else if (IS_ASCII(*p)) {
563 } else if (iseuckanji(*p) && iseuckanji(*(p + 1))) {
564 if (*p >= 0xfd && *p <= 0xfe)
566 else if (guessed == C_SHIFT_JIS) {
567 if ((issjiskanji1(*p) &&
568 issjiskanji2(*(p + 1))) ||
570 guessed = C_SHIFT_JIS;
576 } else if (issjiskanji1(*p) && issjiskanji2(*(p + 1))) {
577 if (iseuchwkana1(*p) && iseuchwkana2(*(p + 1)))
578 guessed = C_SHIFT_JIS;
582 } else if (issjishwkana(*p)) {
583 guessed = C_SHIFT_JIS;
593 static void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
595 conv_jistoutf8(outbuf, outlen, inbuf);
598 static void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
600 conv_sjistoutf8(outbuf, outlen, inbuf);
603 static void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
605 conv_euctoutf8(outbuf, outlen, inbuf);
608 void conv_utf8todisp(gchar *outbuf, gint outlen, const gchar *inbuf)
610 if (g_utf8_validate(inbuf, -1, NULL) == TRUE)
611 strncpy2(outbuf, inbuf, outlen);
613 conv_ustodisp(outbuf, outlen, inbuf);
616 static void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
618 conv_anytoutf8(outbuf, outlen, inbuf);
619 if (g_utf8_validate(outbuf, -1, NULL) != TRUE)
620 conv_unreadable_8bit(outbuf);
623 static void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
625 strncpy2(outbuf, inbuf, outlen);
626 conv_unreadable_8bit(outbuf);
629 void conv_localetodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
633 codeconv_set_strict(TRUE);
634 tmpstr = conv_iconv_strdup(inbuf, conv_get_locale_charset_str(),
636 codeconv_set_strict(FALSE);
637 if (tmpstr && g_utf8_validate(tmpstr, -1, NULL)) {
638 strncpy2(outbuf, tmpstr, outlen);
641 } else if (tmpstr && !g_utf8_validate(tmpstr, -1, NULL)) {
643 codeconv_set_strict(TRUE);
644 tmpstr = conv_iconv_strdup(inbuf,
645 conv_get_locale_charset_str_no_utf8(),
647 codeconv_set_strict(FALSE);
649 if (tmpstr && g_utf8_validate(tmpstr, -1, NULL)) {
650 strncpy2(outbuf, tmpstr, outlen);
655 conv_utf8todisp(outbuf, outlen, inbuf);
659 static void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf)
661 strncpy2(outbuf, inbuf, outlen);
665 conv_get_fallback_for_private_encoding(const gchar *encoding)
667 if (encoding && (encoding[0] == 'X' || encoding[0] == 'x') &&
668 encoding[1] == '-') {
669 if (!g_ascii_strcasecmp(encoding, CS_X_GBK))
676 CodeConverter *conv_code_converter_new(const gchar *src_charset)
680 src_charset = conv_get_fallback_for_private_encoding(src_charset);
682 conv = g_new0(CodeConverter, 1);
683 conv->code_conv_func = conv_get_code_conv_func(src_charset, NULL);
684 conv->charset_str = g_strdup(src_charset);
685 conv->charset = conv_get_charset_from_str(src_charset);
690 void conv_code_converter_destroy(CodeConverter *conv)
692 g_free(conv->charset_str);
696 gint conv_convert(CodeConverter *conv, gchar *outbuf, gint outlen,
699 if (conv->code_conv_func != conv_noconv)
700 conv->code_conv_func(outbuf, outlen, inbuf);
704 str = conv_iconv_strdup(inbuf, conv->charset_str, NULL);
708 strncpy2(outbuf, str, outlen);
716 gchar *conv_codeset_strdup(const gchar *inbuf,
717 const gchar *src_code, const gchar *dest_code)
721 CodeConvFunc conv_func;
723 if (!strcmp2(src_code, dest_code))
724 return g_strdup(inbuf);
726 src_code = conv_get_fallback_for_private_encoding(src_code);
727 conv_func = conv_get_code_conv_func(src_code, dest_code);
728 if (conv_func != conv_noconv) {
729 len = (strlen(inbuf) + 1) * 3;
731 if (!buf) return NULL;
733 conv_func(buf, len, inbuf);
734 return g_realloc(buf, strlen(buf) + 1);
737 return conv_iconv_strdup(inbuf, src_code, dest_code);
740 static CodeConvFunc conv_get_code_conv_func(const gchar *src_charset_str,
741 const gchar *dest_charset_str)
743 CodeConvFunc code_conv = conv_noconv;
745 CharSet dest_charset;
747 if (!src_charset_str)
748 src_charset = conv_get_locale_charset();
750 src_charset = conv_get_charset_from_str(src_charset_str);
752 /* auto detection mode */
753 if (!src_charset_str && !dest_charset_str) {
754 if (conv_is_ja_locale())
755 return conv_anytodisp;
760 dest_charset = conv_get_charset_from_str(dest_charset_str);
762 if (dest_charset == C_US_ASCII)
763 return conv_ustodisp;
765 switch (src_charset) {
783 case C_ISO_2022_JP_2:
784 case C_ISO_2022_JP_3:
785 if (dest_charset == C_AUTO)
786 code_conv = conv_jistodisp;
787 else if (dest_charset == C_EUC_JP)
788 code_conv = conv_jistoeuc;
789 else if (dest_charset == C_UTF_8)
790 code_conv = conv_jistoutf8;
793 if (dest_charset == C_AUTO)
794 code_conv = conv_sjistodisp;
795 else if (dest_charset == C_EUC_JP)
796 code_conv = conv_sjistoeuc;
797 else if (dest_charset == C_UTF_8)
798 code_conv = conv_sjistoutf8;
801 if (dest_charset == C_AUTO)
802 code_conv = conv_euctodisp;
803 else if (dest_charset == C_ISO_2022_JP ||
804 dest_charset == C_ISO_2022_JP_2 ||
805 dest_charset == C_ISO_2022_JP_3)
806 code_conv = conv_euctojis;
807 else if (dest_charset == C_UTF_8)
808 code_conv = conv_euctoutf8;
811 if (dest_charset == C_EUC_JP)
812 code_conv = conv_utf8toeuc;
813 else if (dest_charset == C_ISO_2022_JP ||
814 dest_charset == C_ISO_2022_JP_2 ||
815 dest_charset == C_ISO_2022_JP_3)
816 code_conv = conv_utf8tojis;
825 static gchar *conv_iconv_strdup(const gchar *inbuf,
826 const gchar *src_code, const gchar *dest_code)
831 if (!src_code && !dest_code &&
832 g_utf8_validate(inbuf, -1, NULL))
833 return g_strdup(inbuf);
836 src_code = conv_get_outgoing_charset_str();
838 dest_code = CS_INTERNAL;
840 /* don't convert if src and dest codeset are identical */
841 if (!strcasecmp(src_code, dest_code))
842 return g_strdup(inbuf);
844 /* don't convert if dest codeset is US-ASCII */
845 if (!strcasecmp(src_code, CS_US_ASCII))
846 return g_strdup(inbuf);
848 /* don't convert if dest codeset is US-ASCII */
849 if (!strcasecmp(dest_code, CS_US_ASCII))
850 return g_strdup(inbuf);
852 cd = iconv_open(dest_code, src_code);
853 if (cd == (iconv_t)-1)
856 outbuf = conv_iconv_strdup_with_cd(inbuf, cd);
863 gchar *conv_iconv_strdup_with_cd(const gchar *inbuf, iconv_t cd)
865 const gchar *inbuf_p;
876 in_size = strlen(inbuf);
878 out_size = (in_size + 1) * 2;
879 outbuf = g_malloc(out_size);
883 #define EXPAND_BUF() \
885 len = outbuf_p - outbuf; \
887 outbuf = g_realloc(outbuf, out_size); \
888 outbuf_p = outbuf + len; \
889 out_left = out_size - len; \
892 while ((n_conv = iconv(cd, (ICONV_CONST gchar **)&inbuf_p, &in_left,
893 &outbuf_p, &out_left)) == (size_t)-1) {
894 if (EILSEQ == errno) {
899 //g_print("iconv(): at %d: %s\n", in_size - in_left, g_strerror(errno));
905 *outbuf_p++ = SUBST_CHAR;
907 } else if (EINVAL == errno) {
909 } else if (E2BIG == errno) {
912 g_warning("conv_iconv_strdup(): %s\n",
918 while ((n_conv = iconv(cd, NULL, NULL, &outbuf_p, &out_left)) ==
920 if (E2BIG == errno) {
923 g_warning("conv_iconv_strdup(): %s\n",
931 len = outbuf_p - outbuf;
932 outbuf = g_realloc(outbuf, len + 1);
938 static const struct {
942 {C_US_ASCII, CS_US_ASCII},
943 {C_US_ASCII, CS_ANSI_X3_4_1968},
946 {C_ISO_8859_1, CS_ISO_8859_1},
947 {C_ISO_8859_2, CS_ISO_8859_2},
948 {C_ISO_8859_3, CS_ISO_8859_3},
949 {C_ISO_8859_4, CS_ISO_8859_4},
950 {C_ISO_8859_5, CS_ISO_8859_5},
951 {C_ISO_8859_6, CS_ISO_8859_6},
952 {C_ISO_8859_7, CS_ISO_8859_7},
953 {C_ISO_8859_8, CS_ISO_8859_8},
954 {C_ISO_8859_9, CS_ISO_8859_9},
955 {C_ISO_8859_10, CS_ISO_8859_10},
956 {C_ISO_8859_11, CS_ISO_8859_11},
957 {C_ISO_8859_13, CS_ISO_8859_13},
958 {C_ISO_8859_14, CS_ISO_8859_14},
959 {C_ISO_8859_15, CS_ISO_8859_15},
960 {C_BALTIC, CS_BALTIC},
961 {C_CP1250, CS_CP1250},
962 {C_CP1251, CS_CP1251},
963 {C_CP1252, CS_CP1252},
964 {C_CP1253, CS_CP1253},
965 {C_CP1254, CS_CP1254},
966 {C_CP1255, CS_CP1255},
967 {C_CP1256, CS_CP1256},
968 {C_CP1257, CS_CP1257},
969 {C_CP1258, CS_CP1258},
970 {C_WINDOWS_1250, CS_WINDOWS_1250},
971 {C_WINDOWS_1251, CS_WINDOWS_1251},
972 {C_WINDOWS_1252, CS_WINDOWS_1252},
973 {C_WINDOWS_1253, CS_WINDOWS_1253},
974 {C_WINDOWS_1254, CS_WINDOWS_1254},
975 {C_WINDOWS_1255, CS_WINDOWS_1255},
976 {C_WINDOWS_1256, CS_WINDOWS_1256},
977 {C_WINDOWS_1257, CS_WINDOWS_1257},
978 {C_WINDOWS_1258, CS_WINDOWS_1258},
979 {C_KOI8_R, CS_KOI8_R},
980 {C_KOI8_T, CS_KOI8_T},
981 {C_KOI8_U, CS_KOI8_U},
982 {C_ISO_2022_JP, CS_ISO_2022_JP},
983 {C_ISO_2022_JP_2, CS_ISO_2022_JP_2},
984 {C_ISO_2022_JP_3, CS_ISO_2022_JP_3},
985 {C_EUC_JP, CS_EUC_JP},
986 {C_EUC_JP, CS_EUCJP},
987 {C_EUC_JP_MS, CS_EUC_JP_MS},
988 {C_SHIFT_JIS, CS_SHIFT_JIS},
989 {C_SHIFT_JIS, CS_SHIFT__JIS},
990 {C_SHIFT_JIS, CS_SJIS},
991 {C_ISO_2022_KR, CS_ISO_2022_KR},
992 {C_EUC_KR, CS_EUC_KR},
993 {C_ISO_2022_CN, CS_ISO_2022_CN},
994 {C_EUC_CN, CS_EUC_CN},
995 {C_GB2312, CS_GB2312},
997 {C_EUC_TW, CS_EUC_TW},
999 {C_BIG5_HKSCS, CS_BIG5_HKSCS},
1000 {C_TIS_620, CS_TIS_620},
1001 {C_WINDOWS_874, CS_WINDOWS_874},
1002 {C_GEORGIAN_PS, CS_GEORGIAN_PS},
1003 {C_TCVN5712_1, CS_TCVN5712_1},
1006 static const struct {
1007 gchar *const locale;
1009 CharSet out_charset;
1010 } locale_table[] = {
1011 {"ja_JP.eucJP" , C_EUC_JP , C_ISO_2022_JP},
1012 {"ja_JP.EUC-JP" , C_EUC_JP , C_ISO_2022_JP},
1013 {"ja_JP.EUC" , C_EUC_JP , C_ISO_2022_JP},
1014 {"ja_JP.ujis" , C_EUC_JP , C_ISO_2022_JP},
1015 {"ja_JP.SJIS" , C_SHIFT_JIS , C_ISO_2022_JP},
1016 {"ja_JP.JIS" , C_ISO_2022_JP , C_ISO_2022_JP},
1018 {"ja_JP" , C_SHIFT_JIS , C_ISO_2022_JP},
1020 {"ja_JP" , C_EUC_JP , C_ISO_2022_JP},
1022 {"ko_KR.EUC-KR" , C_EUC_KR , C_EUC_KR},
1023 {"ko_KR" , C_EUC_KR , C_EUC_KR},
1024 {"zh_CN.GB2312" , C_GB2312 , C_GB2312},
1025 {"zh_CN.GBK" , C_GBK , C_GBK},
1026 {"zh_CN" , C_GB2312 , C_GB2312},
1027 {"zh_HK" , C_BIG5_HKSCS , C_BIG5_HKSCS},
1028 {"zh_TW.eucTW" , C_EUC_TW , C_BIG5},
1029 {"zh_TW.EUC-TW" , C_EUC_TW , C_BIG5},
1030 {"zh_TW.Big5" , C_BIG5 , C_BIG5},
1031 {"zh_TW" , C_BIG5 , C_BIG5},
1033 {"ru_RU.KOI8-R" , C_KOI8_R , C_KOI8_R},
1034 {"ru_RU.KOI8R" , C_KOI8_R , C_KOI8_R},
1035 {"ru_RU.CP1251" , C_WINDOWS_1251, C_KOI8_R},
1036 {"ru_RU" , C_ISO_8859_5 , C_KOI8_R},
1037 {"tg_TJ" , C_KOI8_T , C_KOI8_T},
1038 {"ru_UA" , C_KOI8_U , C_KOI8_U},
1039 {"uk_UA.CP1251" , C_WINDOWS_1251, C_KOI8_U},
1040 {"uk_UA" , C_KOI8_U , C_KOI8_U},
1042 {"be_BY" , C_WINDOWS_1251, C_WINDOWS_1251},
1043 {"bg_BG" , C_WINDOWS_1251, C_WINDOWS_1251},
1045 {"yi_US" , C_WINDOWS_1255, C_WINDOWS_1255},
1047 {"af_ZA" , C_ISO_8859_1 , C_ISO_8859_1},
1048 {"br_FR" , C_ISO_8859_1 , C_ISO_8859_1},
1049 {"ca_ES" , C_ISO_8859_1 , C_ISO_8859_1},
1050 {"da_DK" , C_ISO_8859_1 , C_ISO_8859_1},
1051 {"de_AT" , C_ISO_8859_1 , C_ISO_8859_1},
1052 {"de_BE" , C_ISO_8859_1 , C_ISO_8859_1},
1053 {"de_CH" , C_ISO_8859_1 , C_ISO_8859_1},
1054 {"de_DE" , C_ISO_8859_1 , C_ISO_8859_1},
1055 {"de_LU" , C_ISO_8859_1 , C_ISO_8859_1},
1056 {"en_AU" , C_ISO_8859_1 , C_ISO_8859_1},
1057 {"en_BW" , C_ISO_8859_1 , C_ISO_8859_1},
1058 {"en_CA" , C_ISO_8859_1 , C_ISO_8859_1},
1059 {"en_DK" , C_ISO_8859_1 , C_ISO_8859_1},
1060 {"en_GB" , C_ISO_8859_1 , C_ISO_8859_1},
1061 {"en_HK" , C_ISO_8859_1 , C_ISO_8859_1},
1062 {"en_IE" , C_ISO_8859_1 , C_ISO_8859_1},
1063 {"en_NZ" , C_ISO_8859_1 , C_ISO_8859_1},
1064 {"en_PH" , C_ISO_8859_1 , C_ISO_8859_1},
1065 {"en_SG" , C_ISO_8859_1 , C_ISO_8859_1},
1066 {"en_US" , C_ISO_8859_1 , C_ISO_8859_1},
1067 {"en_ZA" , C_ISO_8859_1 , C_ISO_8859_1},
1068 {"en_ZW" , C_ISO_8859_1 , C_ISO_8859_1},
1069 {"es_AR" , C_ISO_8859_1 , C_ISO_8859_1},
1070 {"es_BO" , C_ISO_8859_1 , C_ISO_8859_1},
1071 {"es_CL" , C_ISO_8859_1 , C_ISO_8859_1},
1072 {"es_CO" , C_ISO_8859_1 , C_ISO_8859_1},
1073 {"es_CR" , C_ISO_8859_1 , C_ISO_8859_1},
1074 {"es_DO" , C_ISO_8859_1 , C_ISO_8859_1},
1075 {"es_EC" , C_ISO_8859_1 , C_ISO_8859_1},
1076 {"es_ES" , C_ISO_8859_1 , C_ISO_8859_1},
1077 {"es_GT" , C_ISO_8859_1 , C_ISO_8859_1},
1078 {"es_HN" , C_ISO_8859_1 , C_ISO_8859_1},
1079 {"es_MX" , C_ISO_8859_1 , C_ISO_8859_1},
1080 {"es_NI" , C_ISO_8859_1 , C_ISO_8859_1},
1081 {"es_PA" , C_ISO_8859_1 , C_ISO_8859_1},
1082 {"es_PE" , C_ISO_8859_1 , C_ISO_8859_1},
1083 {"es_PR" , C_ISO_8859_1 , C_ISO_8859_1},
1084 {"es_PY" , C_ISO_8859_1 , C_ISO_8859_1},
1085 {"es_SV" , C_ISO_8859_1 , C_ISO_8859_1},
1086 {"es_US" , C_ISO_8859_1 , C_ISO_8859_1},
1087 {"es_UY" , C_ISO_8859_1 , C_ISO_8859_1},
1088 {"es_VE" , C_ISO_8859_1 , C_ISO_8859_1},
1089 {"et_EE" , C_ISO_8859_1 , C_ISO_8859_1},
1090 {"eu_ES" , C_ISO_8859_1 , C_ISO_8859_1},
1091 {"fi_FI" , C_ISO_8859_1 , C_ISO_8859_1},
1092 {"fo_FO" , C_ISO_8859_1 , C_ISO_8859_1},
1093 {"fr_BE" , C_ISO_8859_1 , C_ISO_8859_1},
1094 {"fr_CA" , C_ISO_8859_1 , C_ISO_8859_1},
1095 {"fr_CH" , C_ISO_8859_1 , C_ISO_8859_1},
1096 {"fr_FR" , C_ISO_8859_1 , C_ISO_8859_1},
1097 {"fr_LU" , C_ISO_8859_1 , C_ISO_8859_1},
1098 {"ga_IE" , C_ISO_8859_1 , C_ISO_8859_1},
1099 {"gl_ES" , C_ISO_8859_1 , C_ISO_8859_1},
1100 {"gv_GB" , C_ISO_8859_1 , C_ISO_8859_1},
1101 {"id_ID" , C_ISO_8859_1 , C_ISO_8859_1},
1102 {"is_IS" , C_ISO_8859_1 , C_ISO_8859_1},
1103 {"it_CH" , C_ISO_8859_1 , C_ISO_8859_1},
1104 {"it_IT" , C_ISO_8859_1 , C_ISO_8859_1},
1105 {"kl_GL" , C_ISO_8859_1 , C_ISO_8859_1},
1106 {"kw_GB" , C_ISO_8859_1 , C_ISO_8859_1},
1107 {"ms_MY" , C_ISO_8859_1 , C_ISO_8859_1},
1108 {"nl_BE" , C_ISO_8859_1 , C_ISO_8859_1},
1109 {"nl_NL" , C_ISO_8859_1 , C_ISO_8859_1},
1110 {"nb_NO" , C_ISO_8859_1 , C_ISO_8859_1},
1111 {"nn_NO" , C_ISO_8859_1 , C_ISO_8859_1},
1112 {"no_NO" , C_ISO_8859_1 , C_ISO_8859_1},
1113 {"oc_FR" , C_ISO_8859_1 , C_ISO_8859_1},
1114 {"pt_BR" , C_ISO_8859_1 , C_ISO_8859_1},
1115 {"pt_PT" , C_ISO_8859_1 , C_ISO_8859_1},
1116 {"sq_AL" , C_ISO_8859_1 , C_ISO_8859_1},
1117 {"sv_FI" , C_ISO_8859_1 , C_ISO_8859_1},
1118 {"sv_SE" , C_ISO_8859_1 , C_ISO_8859_1},
1119 {"tl_PH" , C_ISO_8859_1 , C_ISO_8859_1},
1120 {"uz_UZ" , C_ISO_8859_1 , C_ISO_8859_1},
1121 {"wa_BE" , C_ISO_8859_1 , C_ISO_8859_1},
1123 {"bs_BA" , C_ISO_8859_2 , C_ISO_8859_2},
1124 {"cs_CZ" , C_ISO_8859_2 , C_ISO_8859_2},
1125 {"hr_HR" , C_ISO_8859_2 , C_ISO_8859_2},
1126 {"hu_HU" , C_ISO_8859_2 , C_ISO_8859_2},
1127 {"pl_PL" , C_ISO_8859_2 , C_ISO_8859_2},
1128 {"ro_RO" , C_ISO_8859_2 , C_ISO_8859_2},
1129 {"sk_SK" , C_ISO_8859_2 , C_ISO_8859_2},
1130 {"sl_SI" , C_ISO_8859_2 , C_ISO_8859_2},
1132 {"sr_YU@cyrillic" , C_ISO_8859_5 , C_ISO_8859_5},
1133 {"sr_YU" , C_ISO_8859_2 , C_ISO_8859_2},
1135 {"mt_MT" , C_ISO_8859_3 , C_ISO_8859_3},
1137 {"lt_LT.iso88594" , C_ISO_8859_4 , C_ISO_8859_4},
1138 {"lt_LT.ISO8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
1139 {"lt_LT.ISO_8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
1140 {"lt_LT" , C_ISO_8859_13 , C_ISO_8859_13},
1142 {"mk_MK" , C_ISO_8859_5 , C_ISO_8859_5},
1144 {"ar_AE" , C_ISO_8859_6 , C_ISO_8859_6},
1145 {"ar_BH" , C_ISO_8859_6 , C_ISO_8859_6},
1146 {"ar_DZ" , C_ISO_8859_6 , C_ISO_8859_6},
1147 {"ar_EG" , C_ISO_8859_6 , C_ISO_8859_6},
1148 {"ar_IQ" , C_ISO_8859_6 , C_ISO_8859_6},
1149 {"ar_JO" , C_ISO_8859_6 , C_ISO_8859_6},
1150 {"ar_KW" , C_ISO_8859_6 , C_ISO_8859_6},
1151 {"ar_LB" , C_ISO_8859_6 , C_ISO_8859_6},
1152 {"ar_LY" , C_ISO_8859_6 , C_ISO_8859_6},
1153 {"ar_MA" , C_ISO_8859_6 , C_ISO_8859_6},
1154 {"ar_OM" , C_ISO_8859_6 , C_ISO_8859_6},
1155 {"ar_QA" , C_ISO_8859_6 , C_ISO_8859_6},
1156 {"ar_SA" , C_ISO_8859_6 , C_ISO_8859_6},
1157 {"ar_SD" , C_ISO_8859_6 , C_ISO_8859_6},
1158 {"ar_SY" , C_ISO_8859_6 , C_ISO_8859_6},
1159 {"ar_TN" , C_ISO_8859_6 , C_ISO_8859_6},
1160 {"ar_YE" , C_ISO_8859_6 , C_ISO_8859_6},
1162 {"el_GR" , C_ISO_8859_7 , C_ISO_8859_7},
1163 {"he_IL" , C_ISO_8859_8 , C_ISO_8859_8},
1164 {"iw_IL" , C_ISO_8859_8 , C_ISO_8859_8},
1165 {"tr_TR" , C_ISO_8859_9 , C_ISO_8859_9},
1167 {"lv_LV" , C_ISO_8859_13 , C_ISO_8859_13},
1168 {"mi_NZ" , C_ISO_8859_13 , C_ISO_8859_13},
1170 {"cy_GB" , C_ISO_8859_14 , C_ISO_8859_14},
1172 {"ar_IN" , C_UTF_8 , C_UTF_8},
1173 {"en_IN" , C_UTF_8 , C_UTF_8},
1174 {"se_NO" , C_UTF_8 , C_UTF_8},
1175 {"ta_IN" , C_UTF_8 , C_UTF_8},
1176 {"te_IN" , C_UTF_8 , C_UTF_8},
1177 {"ur_PK" , C_UTF_8 , C_UTF_8},
1179 {"th_TH" , C_TIS_620 , C_TIS_620},
1180 /* {"th_TH" , C_WINDOWS_874}, */
1181 /* {"th_TH" , C_ISO_8859_11}, */
1183 {"ka_GE" , C_GEORGIAN_PS , C_GEORGIAN_PS},
1184 {"vi_VN.TCVN" , C_TCVN5712_1 , C_TCVN5712_1},
1186 {"C" , C_US_ASCII , C_US_ASCII},
1187 {"POSIX" , C_US_ASCII , C_US_ASCII},
1188 {"ANSI_X3.4-1968" , C_US_ASCII , C_US_ASCII},
1191 static GHashTable *conv_get_charset_to_str_table(void)
1193 static GHashTable *table;
1199 table = g_hash_table_new(NULL, g_direct_equal);
1201 for (i = 0; i < sizeof(charsets) / sizeof(charsets[0]); i++) {
1202 if (g_hash_table_lookup(table, GUINT_TO_POINTER(charsets[i].charset))
1205 (table, GUINT_TO_POINTER(charsets[i].charset),
1213 static GHashTable *conv_get_charset_from_str_table(void)
1215 static GHashTable *table;
1221 table = g_hash_table_new(str_case_hash, str_case_equal);
1223 for (i = 0; i < sizeof(charsets) / sizeof(charsets[0]); i++) {
1224 g_hash_table_insert(table, charsets[i].name,
1225 GUINT_TO_POINTER(charsets[i].charset));
1231 const gchar *conv_get_charset_str(CharSet charset)
1235 table = conv_get_charset_to_str_table();
1236 return g_hash_table_lookup(table, GUINT_TO_POINTER(charset));
1239 CharSet conv_get_charset_from_str(const gchar *charset)
1243 if (!charset) return C_AUTO;
1245 table = conv_get_charset_from_str_table();
1246 return GPOINTER_TO_UINT(g_hash_table_lookup(table, charset));
1249 static CharSet conv_get_locale_charset(void)
1251 static CharSet cur_charset = -1;
1252 const gchar *cur_locale;
1256 if (cur_charset != -1)
1259 cur_locale = conv_get_current_locale();
1261 cur_charset = C_US_ASCII;
1265 if (strcasestr(cur_locale, ".UTF-8") ||
1266 strcasestr(cur_locale, ".utf8")) {
1267 cur_charset = C_UTF_8;
1271 if ((p = strcasestr(cur_locale, "@euro")) && p[5] == '\0') {
1272 cur_charset = C_ISO_8859_15;
1276 for (i = 0; i < sizeof(locale_table) / sizeof(locale_table[0]); i++) {
1279 /* "ja_JP.EUC" matches with "ja_JP.eucJP", "ja_JP.EUC" and
1280 "ja_JP". "ja_JP" matches with "ja_JP.xxxx" and "ja" */
1281 if (!g_ascii_strncasecmp(cur_locale, locale_table[i].locale,
1282 strlen(locale_table[i].locale))) {
1283 cur_charset = locale_table[i].charset;
1285 } else if ((p = strchr(locale_table[i].locale, '_')) &&
1286 !strchr(p + 1, '.')) {
1287 if (strlen(cur_locale) == 2 &&
1288 !g_ascii_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
1289 cur_charset = locale_table[i].charset;
1295 cur_charset = C_AUTO;
1299 static CharSet conv_get_locale_charset_no_utf8(void)
1301 static CharSet cur_charset = -1;
1302 const gchar *cur_locale;
1307 if (prefs_common.broken_are_utf8)
1308 return conv_get_locale_charset();
1310 if (cur_charset != -1)
1313 cur_locale = conv_get_current_locale();
1315 cur_charset = C_US_ASCII;
1319 if (strcasestr(cur_locale, "UTF-8")) {
1320 tmp = g_strdup(cur_locale);
1321 *(strcasestr(tmp, ".UTF-8")) = '\0';
1325 if ((p = strcasestr(cur_locale, "@euro")) && p[5] == '\0') {
1326 cur_charset = C_ISO_8859_15;
1330 for (i = 0; i < sizeof(locale_table) / sizeof(locale_table[0]); i++) {
1333 /* "ja_JP.EUC" matches with "ja_JP.eucJP", "ja_JP.EUC" and
1334 "ja_JP". "ja_JP" matches with "ja_JP.xxxx" and "ja" */
1335 if (!g_ascii_strncasecmp(cur_locale, locale_table[i].locale,
1336 strlen(locale_table[i].locale))) {
1337 cur_charset = locale_table[i].charset;
1339 } else if ((p = strchr(locale_table[i].locale, '_')) &&
1340 !strchr(p + 1, '.')) {
1341 if (strlen(cur_locale) == 2 &&
1342 !g_ascii_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
1343 cur_charset = locale_table[i].charset;
1349 cur_charset = C_AUTO;
1353 const gchar *conv_get_locale_charset_str(void)
1355 static const gchar *codeset = NULL;
1358 codeset = conv_get_charset_str(conv_get_locale_charset());
1360 return codeset ? codeset : CS_INTERNAL;
1363 const gchar *conv_get_locale_charset_str_no_utf8(void)
1365 static const gchar *codeset = NULL;
1368 codeset = conv_get_charset_str(conv_get_locale_charset_no_utf8());
1370 return codeset ? codeset : CS_INTERNAL;
1373 static CharSet conv_get_outgoing_charset(void)
1375 static CharSet out_charset = -1;
1376 const gchar *cur_locale;
1380 if (out_charset != -1)
1383 cur_locale = conv_get_current_locale();
1385 out_charset = C_AUTO;
1389 if (strcasestr(cur_locale, "UTF-8")) {
1390 out_charset = C_UTF_8;
1394 if ((p = strcasestr(cur_locale, "@euro")) && p[5] == '\0') {
1395 out_charset = C_ISO_8859_15;
1399 for (i = 0; i < sizeof(locale_table) / sizeof(locale_table[0]); i++) {
1402 if (!g_ascii_strncasecmp(cur_locale, locale_table[i].locale,
1403 strlen(locale_table[i].locale))) {
1404 out_charset = locale_table[i].out_charset;
1406 } else if ((p = strchr(locale_table[i].locale, '_')) &&
1407 !strchr(p + 1, '.')) {
1408 if (strlen(cur_locale) == 2 &&
1409 !g_ascii_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
1410 out_charset = locale_table[i].out_charset;
1419 const gchar *conv_get_outgoing_charset_str(void)
1421 CharSet out_charset;
1424 out_charset = conv_get_outgoing_charset();
1425 str = conv_get_charset_str(out_charset);
1427 return str ? str : CS_UTF_8;
1430 const gchar *conv_get_current_locale(void)
1432 const gchar *cur_locale;
1435 cur_locale = g_win32_getlocale();
1437 cur_locale = g_getenv("LC_ALL");
1438 if (!cur_locale) cur_locale = g_getenv("LC_CTYPE");
1439 if (!cur_locale) cur_locale = g_getenv("LANG");
1440 if (!cur_locale) cur_locale = setlocale(LC_CTYPE, NULL);
1441 #endif /* G_OS_WIN32 */
1443 debug_print("current locale: %s\n",
1444 cur_locale ? cur_locale : "(none)");
1449 static gboolean conv_is_ja_locale(void)
1451 static gint is_ja_locale = -1;
1452 const gchar *cur_locale;
1454 if (is_ja_locale != -1)
1455 return is_ja_locale != 0;
1458 cur_locale = conv_get_current_locale();
1460 if (g_ascii_strncasecmp(cur_locale, "ja", 2) == 0)
1464 return is_ja_locale != 0;
1467 gchar *conv_unmime_header(const gchar *str, const gchar *default_encoding)
1469 gchar buf[BUFFSIZE];
1471 if (is_ascii_str(str))
1472 return unmime_header(str);
1474 if (default_encoding) {
1477 utf8_buf = conv_codeset_strdup
1478 (str, default_encoding, CS_INTERNAL);
1482 decoded_str = unmime_header(utf8_buf);
1488 if (conv_is_ja_locale())
1489 conv_anytodisp(buf, sizeof(buf), str);
1491 conv_localetodisp(buf, sizeof(buf), str);
1493 return unmime_header(buf);
1496 #define MAX_LINELEN 76
1497 #define MAX_HARD_LINELEN 996
1498 #define MIMESEP_BEGIN "=?"
1499 #define MIMESEP_END "?="
1501 #define LBREAK_IF_REQUIRED(cond, is_plain_text) \
1503 if (len - (destp - (guchar *)dest) < MAX_LINELEN + 2) { \
1508 if ((cond) && *srcp) { \
1509 if (destp > (guchar *)dest && left < MAX_LINELEN - 1) { \
1510 if (isspace(*(destp - 1))) \
1512 else if (is_plain_text && isspace(*srcp)) \
1517 left = MAX_LINELEN - 1; \
1523 void conv_encode_header_full(gchar *dest, gint len, const gchar *src,
1524 gint header_len, gboolean addr_field,
1525 const gchar *out_encoding_)
1527 const gchar *cur_encoding;
1528 const gchar *out_encoding;
1532 const guchar *srcp = src;
1533 guchar *destp = dest;
1534 gboolean use_base64;
1536 g_return_if_fail(g_utf8_validate(src, -1, NULL) == TRUE);
1538 if (MB_CUR_MAX > 1) {
1540 mimesep_enc = "?B?";
1543 mimesep_enc = "?Q?";
1546 cur_encoding = CS_INTERNAL;
1549 out_encoding = out_encoding_;
1551 out_encoding = conv_get_outgoing_charset_str();
1553 if (!strcmp(out_encoding, CS_US_ASCII))
1554 out_encoding = CS_ISO_8859_1;
1556 mimestr_len = strlen(MIMESEP_BEGIN) + strlen(out_encoding) +
1557 strlen(mimesep_enc) + strlen(MIMESEP_END);
1559 left = MAX_LINELEN - header_len;
1562 LBREAK_IF_REQUIRED(left <= 0, TRUE);
1564 while (isspace(*srcp)) {
1567 LBREAK_IF_REQUIRED(left <= 0, TRUE);
1570 /* output as it is if the next word is ASCII string */
1571 if (!is_next_nonascii(srcp)) {
1574 word_len = get_next_word_len(srcp);
1575 LBREAK_IF_REQUIRED(left < word_len, TRUE);
1576 while (word_len > 0) {
1577 LBREAK_IF_REQUIRED(left + (MAX_HARD_LINELEN - MAX_LINELEN) <= 0, TRUE)
1586 /* don't include parentheses and quotes in encoded strings */
1587 if (addr_field && (*srcp == '(' || *srcp == ')' || *srcp == '"')) {
1588 LBREAK_IF_REQUIRED(left < 2, FALSE);
1599 const guchar *p = srcp;
1601 gint out_enc_str_len;
1602 gint mime_block_len;
1603 gboolean cont = FALSE;
1605 while (*p != '\0') {
1606 if (isspace(*p) && !is_next_nonascii(p + 1))
1608 /* don't include parentheses in encoded
1610 if (addr_field && (*p == '(' || *p == ')' || *p == '"'))
1613 mb_len = g_utf8_skip[*p];
1615 Xstrndup_a(part_str, srcp, cur_len + mb_len, );
1616 out_str = conv_codeset_strdup
1617 (part_str, cur_encoding, out_encoding);
1623 g_warning("conv_encode_header(): code conversion failed\n");
1624 conv_unreadable_8bit(part_str);
1625 out_str = g_strdup(part_str);
1628 out_str_len = strlen(out_str);
1631 out_enc_str_len = B64LEN(out_str_len);
1634 qp_get_q_encoding_len(out_str);
1638 if (mimestr_len + out_enc_str_len <= left) {
1641 } else if (cur_len == 0) {
1642 LBREAK_IF_REQUIRED(1, FALSE);
1651 Xstrndup_a(part_str, srcp, cur_len, );
1652 out_str = conv_codeset_strdup
1653 (part_str, cur_encoding, out_encoding);
1655 g_warning("conv_encode_header(): code conversion failed\n");
1656 conv_unreadable_8bit(part_str);
1657 out_str = g_strdup(part_str);
1659 out_str_len = strlen(out_str);
1662 out_enc_str_len = B64LEN(out_str_len);
1665 qp_get_q_encoding_len(out_str);
1667 Xalloca(enc_str, out_enc_str_len + 1, );
1669 base64_encode(enc_str, out_str, out_str_len);
1671 qp_q_encode(enc_str, out_str);
1675 /* output MIME-encoded string block */
1676 mime_block_len = mimestr_len + strlen(enc_str);
1677 g_snprintf(destp, mime_block_len + 1,
1678 MIMESEP_BEGIN "%s%s%s" MIMESEP_END,
1679 out_encoding, mimesep_enc, enc_str);
1680 destp += mime_block_len;
1683 left -= mime_block_len;
1686 LBREAK_IF_REQUIRED(cont, FALSE);
1696 void conv_encode_header(gchar *dest, gint len, const gchar *src,
1697 gint header_len, gboolean addr_field)
1699 conv_encode_header_full(dest,len,src,header_len,addr_field,NULL);
1702 #undef LBREAK_IF_REQUIRED
1703 gchar *conv_filename_from_utf8(const gchar *utf8_file)
1706 GError *error = NULL;
1708 fs_file = g_filename_from_utf8(utf8_file, -1, NULL, NULL, &error);
1710 g_warning("failed to convert encoding of file name: %s\n",
1712 g_error_free(error);
1715 fs_file = g_strdup(utf8_file);
1720 gchar *conv_filename_to_utf8(const gchar *fs_file)
1722 gchar *utf8_file = NULL;
1723 GError *error = NULL;
1725 utf8_file = g_filename_to_utf8(fs_file, -1, NULL, NULL, &error);
1727 g_warning("failed to convert encoding of file name: %s\n",
1729 g_error_free(error);
1732 if (!utf8_file || !g_utf8_validate(utf8_file, -1, NULL)) {
1734 utf8_file = g_strdup(fs_file);
1735 conv_unreadable_8bit(utf8_file);