/*
* Sylpheed -- a GTK+ based, lightweight, and fast e-mail client
- * Copyright (C) 1999-2003 Hiroyuki Yamamoto
+ * Copyright (C) 1999-2005 Hiroyuki Yamamoto
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
# include <locale.h>
#endif
-#if HAVE_ICONV
-# include <iconv.h>
-#endif
+#include <iconv.h>
#include "intl.h"
#include "codeconv.h"
JIS_AUXKANJI
} JISState;
-#define SUBST_CHAR '_'
+#define SUBST_CHAR 0x5f;
#define ESC '\033'
#define iseuckanji(c) \
state = JIS_AUXKANJI; \
}
-void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
+
+static void conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+
+static void conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf);
+
+static void conv_unreadable_eucjp(gchar *str);
+static void conv_unreadable_8bit(gchar *str);
+static void conv_unreadable_latin(gchar *str);
+
+static void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+
+static void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf);
+
+static void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
guchar *out = outbuf;
*out = '\0';
}
-void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
+#define JIS_HWDAKUTEN 0x5e
+#define JIS_HWHANDAKUTEN 0x5f
+
+static gint conv_jis_hantozen(guchar *outbuf, guchar jis_code, guchar sound_sym)
+{
+ static guint16 h2z_tbl[] = {
+ /* 0x20 - 0x2f */
+ 0x0000, 0x2123, 0x2156, 0x2157, 0x2122, 0x2126, 0x2572, 0x2521,
+ 0x2523, 0x2525, 0x2527, 0x2529, 0x2563, 0x2565, 0x2567, 0x2543,
+ /* 0x30 - 0x3f */
+ 0x213c, 0x2522, 0x2524, 0x2526, 0x2528, 0x252a, 0x252b, 0x252d,
+ 0x252f, 0x2531, 0x2533, 0x2535, 0x2537, 0x2539, 0x253b, 0x253d,
+ /* 0x40 - 0x4f */
+ 0x253f, 0x2541, 0x2544, 0x2546, 0x2548, 0x254a, 0x254b, 0x254c,
+ 0x254d, 0x254e, 0x254f, 0x2552, 0x2555, 0x2558, 0x255b, 0x255e,
+ /* 0x50 - 0x5f */
+ 0x255f, 0x2560, 0x2561, 0x2562, 0x2564, 0x2566, 0x2568, 0x2569,
+ 0x256a, 0x256b, 0x256c, 0x256d, 0x256f, 0x2573, 0x212b, 0x212c
+ };
+
+ static guint16 dakuten_tbl[] = {
+ /* 0x30 - 0x3f */
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x252c, 0x252e,
+ 0x2530, 0x2532, 0x2534, 0x2536, 0x2538, 0x253a, 0x253c, 0x253e,
+ /* 0x40 - 0x4f */
+ 0x2540, 0x2542, 0x2545, 0x2547, 0x2549, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x2550, 0x2553, 0x2556, 0x2559, 0x255c, 0x0000
+ };
+
+ static guint16 handakuten_tbl[] = {
+ /* 0x4a - 0x4e */
+ 0x2551, 0x2554, 0x2557, 0x255a, 0x255d
+ };
+
+ guint16 out_code;
+
+ jis_code &= 0x7f;
+ sound_sym &= 0x7f;
+
+ if (jis_code < 0x21 || jis_code > 0x5f)
+ return 0;
+
+ if (sound_sym == JIS_HWDAKUTEN &&
+ jis_code >= 0x36 && jis_code <= 0x4e) {
+ out_code = dakuten_tbl[jis_code - 0x30];
+ if (out_code != 0) {
+ *outbuf = out_code >> 8;
+ *(outbuf + 1) = out_code & 0xff;
+ return 2;
+ }
+ }
+
+ if (sound_sym == JIS_HWHANDAKUTEN &&
+ jis_code >= 0x4a && jis_code <= 0x4e) {
+ out_code = handakuten_tbl[jis_code - 0x4a];
+ *outbuf = out_code >> 8;
+ *(outbuf + 1) = out_code & 0xff;
+ return 2;
+ }
+
+ out_code = h2z_tbl[jis_code - 0x20];
+ *outbuf = out_code >> 8;
+ *(outbuf + 1) = out_code & 0xff;
+ return 1;
+}
+
+static void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
guchar *out = outbuf;
JISState state = JIS_ASCII;
while (*in != '\0') {
- if (isascii(*in)) {
+ if (IS_ASCII(*in)) {
K_OUT();
*out++ = *in++;
} else if (iseuckanji(*in)) {
K_OUT();
*out++ = SUBST_CHAR;
in++;
- if (*in != '\0' && !isascii(*in)) {
+ if (*in != '\0' && !IS_ASCII(*in)) {
*out++ = SUBST_CHAR;
in++;
}
}
} else if (iseuchwkana1(*in)) {
- in++;
- if (iseuchwkana2(*in)) {
- HW_IN();
- *out++ = *in++ & 0x7f;
+ if (iseuchwkana2(*(in + 1))) {
+ if (prefs_common.allow_jisx0201_kana) {
+ HW_IN();
+ in++;
+ *out++ = *in++ & 0x7f;
+ } else {
+ guchar jis_ch[2];
+ gint len;
+
+ if (iseuchwkana1(*(in + 2)) &&
+ iseuchwkana2(*(in + 3)))
+ len = conv_jis_hantozen
+ (jis_ch,
+ *(in + 1), *(in + 3));
+ else
+ len = conv_jis_hantozen
+ (jis_ch,
+ *(in + 1), '\0');
+ if (len == 0)
+ in += 2;
+ else {
+ K_IN();
+ in += len * 2;
+ *out++ = jis_ch[0];
+ *out++ = jis_ch[1];
+ }
+ }
} else {
K_OUT();
- if (*in != '\0' && !isascii(*in)) {
+ in++;
+ if (*in != '\0' && !IS_ASCII(*in)) {
*out++ = SUBST_CHAR;
in++;
}
*out++ = *in++ & 0x7f;
} else {
K_OUT();
- if (*in != '\0' && !isascii(*in)) {
+ if (*in != '\0' && !IS_ASCII(*in)) {
*out++ = SUBST_CHAR;
in++;
- if (*in != '\0' && !isascii(*in)) {
+ if (*in != '\0' && !IS_ASCII(*in)) {
*out++ = SUBST_CHAR;
in++;
}
*out = '\0';
}
-void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
guchar *out = outbuf;
while (*in != '\0') {
- if (isascii(*in)) {
+ if (IS_ASCII(*in)) {
*out++ = *in++;
} else if (issjiskanji1(*in)) {
if (issjiskanji2(*(in + 1))) {
} else {
*out++ = SUBST_CHAR;
in++;
- if (*in != '\0' && !isascii(*in)) {
+ if (*in != '\0' && !IS_ASCII(*in)) {
*out++ = SUBST_CHAR;
in++;
}
*out = '\0';
}
-void conv_anytoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+{
+ gchar *eucstr;
+
+ Xalloca(eucstr, outlen, return);
+
+ conv_jistoeuc(eucstr, outlen, inbuf);
+ conv_euctoutf8(outbuf, outlen, eucstr);
+}
+
+static void conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+{
+ gchar *tmpstr;
+
+ tmpstr = conv_iconv_strdup(inbuf, CS_SHIFT_JIS, CS_UTF_8);
+ if (tmpstr) {
+ strncpy2(outbuf, tmpstr, outlen);
+ g_free(tmpstr);
+ } else
+ strncpy2(outbuf, inbuf, outlen);
+}
+
+static void conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+{
+ static iconv_t cd = (iconv_t)-1;
+ static gboolean iconv_ok = TRUE;
+ gchar *tmpstr;
+
+ if (cd == (iconv_t)-1) {
+ if (!iconv_ok) {
+ strncpy2(outbuf, inbuf, outlen);
+ return;
+ }
+ cd = iconv_open(CS_UTF_8, CS_EUC_JP_MS);
+ if (cd == (iconv_t)-1) {
+ cd = iconv_open(CS_UTF_8, CS_EUC_JP);
+ if (cd == (iconv_t)-1) {
+ g_warning("conv_euctoutf8(): %s\n",
+ g_strerror(errno));
+ iconv_ok = FALSE;
+ strncpy2(outbuf, inbuf, outlen);
+ return;
+ }
+ }
+ }
+
+ tmpstr = conv_iconv_strdup_with_cd(inbuf, cd);
+ if (tmpstr) {
+ strncpy2(outbuf, tmpstr, outlen);
+ g_free(tmpstr);
+ } else
+ strncpy2(outbuf, inbuf, outlen);
+}
+
+static void conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
{
switch (conv_guess_ja_encoding(inbuf)) {
case C_ISO_2022_JP:
- conv_jistoeuc(outbuf, outlen, inbuf);
+ conv_jistoutf8(outbuf, outlen, inbuf);
break;
case C_SHIFT_JIS:
- conv_sjistoeuc(outbuf, outlen, inbuf);
+ conv_sjistoutf8(outbuf, outlen, inbuf);
+ break;
+ case C_EUC_JP:
+ conv_euctoutf8(outbuf, outlen, inbuf);
break;
default:
strncpy2(outbuf, inbuf, outlen);
}
}
-void conv_anytojis(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- switch (conv_guess_ja_encoding(inbuf)) {
- case C_EUC_JP:
- conv_euctojis(outbuf, outlen, inbuf);
- break;
- default:
- strncpy2(outbuf, inbuf, outlen);
- break;
+ static iconv_t cd = (iconv_t)-1;
+ static gboolean iconv_ok = TRUE;
+ gchar *tmpstr;
+
+ if (cd == (iconv_t)-1) {
+ if (!iconv_ok) {
+ strncpy2(outbuf, inbuf, outlen);
+ return;
+ }
+ cd = iconv_open(CS_EUC_JP_MS, CS_UTF_8);
+ if (cd == (iconv_t)-1) {
+ cd = iconv_open(CS_EUC_JP, CS_UTF_8);
+ if (cd == (iconv_t)-1) {
+ g_warning("conv_utf8toeuc(): %s\n",
+ g_strerror(errno));
+ iconv_ok = FALSE;
+ strncpy2(outbuf, inbuf, outlen);
+ return;
+ }
+ }
}
+
+ tmpstr = conv_iconv_strdup_with_cd(inbuf, cd);
+ if (tmpstr) {
+ strncpy2(outbuf, tmpstr, outlen);
+ g_free(tmpstr);
+ } else
+ strncpy2(outbuf, inbuf, outlen);
+}
+
+static void conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf)
+{
+ gchar *eucstr;
+
+ Xalloca(eucstr, outlen, return);
+
+ conv_utf8toeuc(eucstr, outlen, inbuf);
+ conv_euctojis(outbuf, outlen, eucstr);
}
static gchar valid_eucjp_tbl[][96] = {
return (gboolean)valid_eucjp_tbl[c1 - 0xa2][c2 - 0xa0];
if (c1 == 0xcf) {
- if (c2 >= 0xd4 && c2 <= 0xff)
+ if (c2 >= 0xd4 && c2 <= 0xfe)
return FALSE;
} else if (c1 == 0xf4) {
- if (c2 >= 0xa7 && c2 <= 0xff)
+ if (c2 >= 0xa7 && c2 <= 0xfe)
return FALSE;
}
return TRUE;
}
-void conv_unreadable_eucjp(gchar *str)
+static void conv_unreadable_eucjp(gchar *str)
{
register guchar *p = str;
while (*p != '\0') {
- if (isascii(*p)) {
+ if (IS_ASCII(*p)) {
/* convert CR+LF -> LF */
if (*p == '\r' && *(p + 1) == '\n')
memmove(p, p + 1, strlen(p));
/* substitute unprintable code */
*p++ = SUBST_CHAR;
if (*p != '\0') {
- if (isascii(*p))
+ if (IS_ASCII(*p))
p++;
else
*p++ = SUBST_CHAR;
}
}
-void conv_unreadable_8bit(gchar *str)
+static void conv_unreadable_8bit(gchar *str)
{
register guchar *p = str;
/* convert CR+LF -> LF */
if (*p == '\r' && *(p + 1) == '\n')
memmove(p, p + 1, strlen(p));
- else if (!isascii(*p)) *p = SUBST_CHAR;
+ else if (!IS_ASCII(*p)) *p = SUBST_CHAR;
p++;
}
}
-void conv_unreadable_latin(gchar *str)
+static void conv_unreadable_latin(gchar *str)
{
register guchar *p = str;
/* convert CR+LF -> LF */
if (*p == '\r' && *(p + 1) == '\n')
memmove(p, p + 1, strlen(p));
- else if ((*p & 0xff) >= 0x7f && (*p & 0xff) <= 0x9f)
+ else if ((*p & 0xff) >= 0x7f)
*p = SUBST_CHAR;
p++;
}
if (guessed == C_US_ASCII)
return C_ISO_2022_JP;
p += 2;
- } else if (isascii(*p)) {
+ } else if (IS_ASCII(*p)) {
p++;
} else if (iseuckanji(*p) && iseuckanji(*(p + 1))) {
if (*p >= 0xfd && *p <= 0xfe)
return guessed;
}
-void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_jistoeuc(outbuf, outlen, inbuf);
- conv_unreadable_eucjp(outbuf);
+ conv_jistoutf8(outbuf, outlen, inbuf);
}
-void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_sjistoeuc(outbuf, outlen, inbuf);
- conv_unreadable_eucjp(outbuf);
+ conv_sjistoutf8(outbuf, outlen, inbuf);
}
-void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- strncpy2(outbuf, inbuf, outlen);
- conv_unreadable_eucjp(outbuf);
+ conv_euctoutf8(outbuf, outlen, inbuf);
}
-void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+void conv_utf8todisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_anytoeuc(outbuf, outlen, inbuf);
- conv_unreadable_eucjp(outbuf);
+ strncpy2(outbuf, inbuf, outlen);
}
-void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- strncpy2(outbuf, inbuf, outlen);
- conv_unreadable_8bit(outbuf);
+ conv_anytoutf8(outbuf, outlen, inbuf);
}
-void conv_latintodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
strncpy2(outbuf, inbuf, outlen);
- conv_unreadable_latin(outbuf);
+ conv_unreadable_8bit(outbuf);
}
-void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf)
+void conv_localetodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- strncpy2(outbuf, inbuf, outlen);
+ gchar *tmpstr;
+
+ tmpstr = conv_iconv_strdup(inbuf, conv_get_locale_charset_str(),
+ CS_INTERNAL);
+ if (tmpstr) {
+ strncpy2(outbuf, tmpstr, outlen);
+ g_free(tmpstr);
+ } else
+ strncpy2(outbuf, inbuf, outlen);
}
-void conv_localetodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf)
{
strncpy2(outbuf, inbuf, outlen);
-
- switch (conv_get_current_charset()) {
- case C_US_ASCII:
- case C_ISO_8859_1:
- case C_ISO_8859_2:
- case C_ISO_8859_4:
- case C_ISO_8859_5:
- case C_ISO_8859_7:
- case C_ISO_8859_8:
- case C_ISO_8859_9:
- case C_ISO_8859_11:
- case C_ISO_8859_13:
- case C_ISO_8859_15:
- conv_unreadable_latin(outbuf);
- break;
- case C_EUC_JP:
- conv_unreadable_eucjp(outbuf);
- break;
- default:
- break;
- }
}
-CodeConverter *conv_code_converter_new(const gchar *charset)
+CodeConverter *conv_code_converter_new(const gchar *src_charset)
{
CodeConverter *conv;
conv = g_new0(CodeConverter, 1);
- conv->code_conv_func = conv_get_code_conv_func(charset, NULL);
- conv->charset_str = g_strdup(charset);
- conv->charset = conv_get_charset_from_str(charset);
+ conv->code_conv_func = conv_get_code_conv_func(src_charset, NULL);
+ conv->charset_str = g_strdup(src_charset);
+ conv->charset = conv_get_charset_from_str(src_charset);
return conv;
}
gint conv_convert(CodeConverter *conv, gchar *outbuf, gint outlen,
const gchar *inbuf)
{
-#if HAVE_ICONV
if (conv->code_conv_func != conv_noconv)
conv->code_conv_func(outbuf, outlen, inbuf);
else {
g_free(str);
}
}
-#else /* !HAVE_ICONV */
- conv->code_conv_func(outbuf, outlen, inbuf);
-#endif
return 0;
}
return g_realloc(buf, strlen(buf) + 1);
}
-#if HAVE_ICONV
return conv_iconv_strdup(inbuf, src_code, dest_code);
-#else
- return g_strdup(inbuf);
-#endif /* HAVE_ICONV */
}
CodeConvFunc conv_get_code_conv_func(const gchar *src_charset_str,
CharSet dest_charset;
if (!src_charset_str)
- src_charset = conv_get_current_charset();
+ src_charset = conv_get_locale_charset();
else
src_charset = conv_get_charset_from_str(src_charset_str);
if (dest_charset == C_US_ASCII)
return conv_ustodisp;
- else if (dest_charset == C_UTF_8 ||
- (dest_charset == C_AUTO &&
- conv_get_current_charset() == C_UTF_8))
- return conv_noconv;
switch (src_charset) {
- case C_ISO_2022_JP:
- case C_ISO_2022_JP_2:
- if (dest_charset == C_AUTO)
- code_conv = conv_jistodisp;
- else if (dest_charset == C_EUC_JP)
- code_conv = conv_jistoeuc;
- break;
case C_US_ASCII:
- if (dest_charset == C_AUTO)
- code_conv = conv_ustodisp;
- break;
case C_ISO_8859_1:
case C_ISO_8859_2:
+ case C_ISO_8859_3:
case C_ISO_8859_4:
case C_ISO_8859_5:
+ case C_ISO_8859_6:
case C_ISO_8859_7:
case C_ISO_8859_8:
case C_ISO_8859_9:
+ case C_ISO_8859_10:
case C_ISO_8859_11:
case C_ISO_8859_13:
+ case C_ISO_8859_14:
case C_ISO_8859_15:
+ break;
+ case C_ISO_2022_JP:
+ case C_ISO_2022_JP_2:
+ case C_ISO_2022_JP_3:
if (dest_charset == C_AUTO)
- code_conv = conv_latintodisp;
+ code_conv = conv_jistodisp;
+ else if (dest_charset == C_EUC_JP)
+ code_conv = conv_jistoeuc;
+ else if (dest_charset == C_UTF_8)
+ code_conv = conv_jistoutf8;
break;
case C_SHIFT_JIS:
if (dest_charset == C_AUTO)
code_conv = conv_sjistodisp;
else if (dest_charset == C_EUC_JP)
code_conv = conv_sjistoeuc;
+ else if (dest_charset == C_UTF_8)
+ code_conv = conv_sjistoutf8;
break;
case C_EUC_JP:
if (dest_charset == C_AUTO)
code_conv = conv_euctodisp;
- else if (dest_charset == C_ISO_2022_JP ||
- dest_charset == C_ISO_2022_JP_2)
+ else if (dest_charset == C_ISO_2022_JP ||
+ dest_charset == C_ISO_2022_JP_2 ||
+ dest_charset == C_ISO_2022_JP_3)
code_conv = conv_euctojis;
+ else if (dest_charset == C_UTF_8)
+ code_conv = conv_euctoutf8;
+ break;
+ case C_UTF_8:
+ if (dest_charset == C_EUC_JP)
+ code_conv = conv_utf8toeuc;
+ else if (dest_charset == C_ISO_2022_JP ||
+ dest_charset == C_ISO_2022_JP_2 ||
+ dest_charset == C_ISO_2022_JP_3)
+ code_conv = conv_utf8tojis;
break;
default:
break;
return code_conv;
}
-#if HAVE_ICONV
gchar *conv_iconv_strdup(const gchar *inbuf,
const gchar *src_code, const gchar *dest_code)
{
iconv_t cd;
- const gchar *inbuf_p;
gchar *outbuf;
- gchar *outbuf_p;
- gint in_size;
- gint in_left;
- gint out_size;
- gint out_left;
- gint n_conv;
if (!src_code)
src_code = conv_get_outgoing_charset_str();
if (!dest_code)
- dest_code = conv_get_current_charset_str();
-
- /* don't convert if current codeset is US-ASCII */
- if (!strcasecmp(dest_code, CS_US_ASCII))
- return g_strdup(inbuf);
+ dest_code = CS_INTERNAL;
/* don't convert if src and dest codeset are identical */
if (!strcasecmp(src_code, dest_code))
return g_strdup(inbuf);
+ /* don't convert if current codeset is US-ASCII */
+ if (!strcasecmp(dest_code, CS_US_ASCII))
+ return g_strdup(inbuf);
+
cd = iconv_open(dest_code, src_code);
if (cd == (iconv_t)-1)
return NULL;
+ outbuf = conv_iconv_strdup_with_cd(inbuf, cd);
+
+ iconv_close(cd);
+
+ return outbuf;
+}
+
+gchar *conv_iconv_strdup_with_cd(const gchar *inbuf, iconv_t cd)
+{
+ const gchar *inbuf_p;
+ gchar *outbuf;
+ gchar *outbuf_p;
+ size_t in_size;
+ size_t in_left;
+ size_t out_size;
+ size_t out_left;
+ size_t n_conv;
+ size_t len;
+
inbuf_p = inbuf;
- in_size = strlen(inbuf) + 1;
+ in_size = strlen(inbuf);
in_left = in_size;
- out_size = in_size * 2;
+ out_size = (in_size + 1) * 2;
outbuf = g_malloc(out_size);
outbuf_p = outbuf;
out_left = out_size;
+#define EXPAND_BUF() \
+{ \
+ len = outbuf_p - outbuf; \
+ out_size *= 2; \
+ outbuf = g_realloc(outbuf, out_size); \
+ outbuf_p = outbuf + len; \
+ out_left = out_size - len; \
+}
+
while ((n_conv = iconv(cd, (ICONV_CONST gchar **)&inbuf_p, &in_left,
- &outbuf_p, &out_left)) < 0) {
+ &outbuf_p, &out_left)) == (size_t)-1) {
if (EILSEQ == errno) {
+ //g_print("iconv(): at %d: %s\n", in_size - in_left, g_strerror(errno));
inbuf_p++;
in_left--;
+ if (out_left == 0) {
+ EXPAND_BUF();
+ }
*outbuf_p++ = SUBST_CHAR;
out_left--;
} else if (EINVAL == errno) {
- *outbuf_p = '\0';
break;
} else if (E2BIG == errno) {
- out_size *= 2;
- outbuf = g_realloc(outbuf, out_size);
- inbuf_p = inbuf;
- in_left = in_size;
- outbuf_p = outbuf;
- out_left = out_size;
+ EXPAND_BUF();
+ } else {
+ g_warning("conv_iconv_strdup(): %s\n",
+ g_strerror(errno));
+ break;
+ }
+ }
+
+ while ((n_conv = iconv(cd, NULL, NULL, &outbuf_p, &out_left)) ==
+ (size_t)-1) {
+ if (E2BIG == errno) {
+ EXPAND_BUF();
} else {
g_warning("conv_iconv_strdup(): %s\n",
g_strerror(errno));
- *outbuf_p = '\0';
break;
}
}
- iconv(cd, NULL, NULL, &outbuf_p, &out_left);
- outbuf = g_realloc(outbuf, strlen(outbuf) + 1);
+#undef EXPAND_BUF
- iconv_close(cd);
+ len = outbuf_p - outbuf;
+ outbuf = g_realloc(outbuf, len + 1);
+ outbuf[len] = '\0';
return outbuf;
}
-#endif /* HAVE_ICONV */
static const struct {
CharSet charset;
{C_US_ASCII, CS_US_ASCII},
{C_US_ASCII, CS_ANSI_X3_4_1968},
{C_UTF_8, CS_UTF_8},
+ {C_UTF_7, CS_UTF_7},
{C_ISO_8859_1, CS_ISO_8859_1},
{C_ISO_8859_2, CS_ISO_8859_2},
+ {C_ISO_8859_3, CS_ISO_8859_3},
{C_ISO_8859_4, CS_ISO_8859_4},
{C_ISO_8859_5, CS_ISO_8859_5},
+ {C_ISO_8859_6, CS_ISO_8859_6},
{C_ISO_8859_7, CS_ISO_8859_7},
{C_ISO_8859_8, CS_ISO_8859_8},
{C_ISO_8859_9, CS_ISO_8859_9},
+ {C_ISO_8859_10, CS_ISO_8859_10},
{C_ISO_8859_11, CS_ISO_8859_11},
{C_ISO_8859_13, CS_ISO_8859_13},
+ {C_ISO_8859_14, CS_ISO_8859_14},
{C_ISO_8859_15, CS_ISO_8859_15},
{C_BALTIC, CS_BALTIC},
+ {C_CP1250, CS_CP1250},
{C_CP1251, CS_CP1251},
+ {C_CP1252, CS_CP1252},
+ {C_CP1253, CS_CP1253},
+ {C_CP1254, CS_CP1254},
+ {C_CP1255, CS_CP1255},
+ {C_CP1256, CS_CP1256},
+ {C_CP1257, CS_CP1257},
+ {C_CP1258, CS_CP1258},
+ {C_WINDOWS_1250, CS_WINDOWS_1250},
{C_WINDOWS_1251, CS_WINDOWS_1251},
+ {C_WINDOWS_1252, CS_WINDOWS_1252},
+ {C_WINDOWS_1253, CS_WINDOWS_1253},
+ {C_WINDOWS_1254, CS_WINDOWS_1254},
+ {C_WINDOWS_1255, CS_WINDOWS_1255},
+ {C_WINDOWS_1256, CS_WINDOWS_1256},
+ {C_WINDOWS_1257, CS_WINDOWS_1257},
+ {C_WINDOWS_1258, CS_WINDOWS_1258},
{C_KOI8_R, CS_KOI8_R},
+ {C_KOI8_T, CS_KOI8_T},
{C_KOI8_U, CS_KOI8_U},
{C_ISO_2022_JP, CS_ISO_2022_JP},
{C_ISO_2022_JP_2, CS_ISO_2022_JP_2},
+ {C_ISO_2022_JP_3, CS_ISO_2022_JP_3},
{C_EUC_JP, CS_EUC_JP},
{C_EUC_JP, CS_EUCJP},
+ {C_EUC_JP_MS, CS_EUC_JP_MS},
{C_SHIFT_JIS, CS_SHIFT_JIS},
{C_SHIFT_JIS, CS_SHIFT__JIS},
{C_SHIFT_JIS, CS_SJIS},
{C_ISO_2022_CN, CS_ISO_2022_CN},
{C_EUC_CN, CS_EUC_CN},
{C_GB2312, CS_GB2312},
+ {C_GBK, CS_GBK},
{C_EUC_TW, CS_EUC_TW},
{C_BIG5, CS_BIG5},
+ {C_BIG5_HKSCS, CS_BIG5_HKSCS},
{C_TIS_620, CS_TIS_620},
{C_WINDOWS_874, CS_WINDOWS_874},
+ {C_GEORGIAN_PS, CS_GEORGIAN_PS},
+ {C_TCVN5712_1, CS_TCVN5712_1},
};
static const struct {
CharSet out_charset;
} locale_table[] = {
{"ja_JP.eucJP" , C_EUC_JP , C_ISO_2022_JP},
- {"ja_JP.ujis" , C_EUC_JP , C_ISO_2022_JP},
+ {"ja_JP.EUC-JP" , C_EUC_JP , C_ISO_2022_JP},
{"ja_JP.EUC" , C_EUC_JP , C_ISO_2022_JP},
+ {"ja_JP.ujis" , C_EUC_JP , C_ISO_2022_JP},
{"ja_JP.SJIS" , C_SHIFT_JIS , C_ISO_2022_JP},
{"ja_JP.JIS" , C_ISO_2022_JP , C_ISO_2022_JP},
{"ja_JP" , C_EUC_JP , C_ISO_2022_JP},
+ {"ko_KR.EUC-KR" , C_EUC_KR , C_EUC_KR},
{"ko_KR" , C_EUC_KR , C_EUC_KR},
{"zh_CN.GB2312" , C_GB2312 , C_GB2312},
+ {"zh_CN.GBK" , C_GBK , C_GB2312},
{"zh_CN" , C_GB2312 , C_GB2312},
+ {"zh_HK" , C_BIG5_HKSCS , C_BIG5_HKSCS},
{"zh_TW.eucTW" , C_EUC_TW , C_BIG5},
+ {"zh_TW.EUC-TW" , C_EUC_TW , C_BIG5},
{"zh_TW.Big5" , C_BIG5 , C_BIG5},
{"zh_TW" , C_BIG5 , C_BIG5},
{"ru_RU.KOI8-R" , C_KOI8_R , C_KOI8_R},
+ {"ru_RU.KOI8R" , C_KOI8_R , C_KOI8_R},
{"ru_RU.CP1251" , C_WINDOWS_1251, C_KOI8_R},
{"ru_RU" , C_ISO_8859_5 , C_KOI8_R},
+ {"tg_TJ" , C_KOI8_T , C_KOI8_T},
{"ru_UA" , C_KOI8_U , C_KOI8_U},
+ {"uk_UA.CP1251" , C_WINDOWS_1251, C_KOI8_U},
{"uk_UA" , C_KOI8_U , C_KOI8_U},
+
{"be_BY" , C_WINDOWS_1251, C_WINDOWS_1251},
{"bg_BG" , C_WINDOWS_1251, C_WINDOWS_1251},
- {"en_US" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"yi_US" , C_WINDOWS_1255, C_WINDOWS_1255},
+
+ {"af_ZA" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"br_FR" , C_ISO_8859_1 , C_ISO_8859_1},
{"ca_ES" , C_ISO_8859_1 , C_ISO_8859_1},
{"da_DK" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"de_AT" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"de_BE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"de_CH" , C_ISO_8859_1 , C_ISO_8859_1},
{"de_DE" , C_ISO_8859_1 , C_ISO_8859_1},
- {"nl_NL" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"de_LU" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_AU" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_BW" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_CA" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_DK" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_GB" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_HK" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_IE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_NZ" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_PH" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_SG" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_US" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_ZA" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"en_ZW" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_AR" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_BO" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_CL" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_CO" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_CR" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_DO" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_EC" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_ES" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_GT" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_HN" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_MX" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_NI" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_PA" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_PE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_PR" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_PY" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_SV" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_US" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_UY" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"es_VE" , C_ISO_8859_1 , C_ISO_8859_1},
{"et_EE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"eu_ES" , C_ISO_8859_1 , C_ISO_8859_1},
{"fi_FI" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"fo_FO" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"fr_BE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"fr_CA" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"fr_CH" , C_ISO_8859_1 , C_ISO_8859_1},
{"fr_FR" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"fr_LU" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"ga_IE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"gl_ES" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"gv_GB" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"id_ID" , C_ISO_8859_1 , C_ISO_8859_1},
{"is_IS" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"it_CH" , C_ISO_8859_1 , C_ISO_8859_1},
{"it_IT" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"kl_GL" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"kw_GB" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"ms_MY" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"nl_BE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"nl_NL" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"nn_NO" , C_ISO_8859_1 , C_ISO_8859_1},
{"no_NO" , C_ISO_8859_1 , C_ISO_8859_1},
- {"pt_PT" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"oc_FR" , C_ISO_8859_1 , C_ISO_8859_1},
{"pt_BR" , C_ISO_8859_1 , C_ISO_8859_1},
- {"es_ES" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"pt_PT" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"sq_AL" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"sv_FI" , C_ISO_8859_1 , C_ISO_8859_1},
{"sv_SE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"tl_PH" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"uz_UZ" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"wa_BE" , C_ISO_8859_1 , C_ISO_8859_1},
+ {"bs_BA" , C_ISO_8859_2 , C_ISO_8859_2},
+ {"cs_CZ" , C_ISO_8859_2 , C_ISO_8859_2},
{"hr_HR" , C_ISO_8859_2 , C_ISO_8859_2},
{"hu_HU" , C_ISO_8859_2 , C_ISO_8859_2},
{"pl_PL" , C_ISO_8859_2 , C_ISO_8859_2},
{"ro_RO" , C_ISO_8859_2 , C_ISO_8859_2},
{"sk_SK" , C_ISO_8859_2 , C_ISO_8859_2},
{"sl_SI" , C_ISO_8859_2 , C_ISO_8859_2},
+
+ {"sr_YU@cyrillic" , C_ISO_8859_5 , C_ISO_8859_5},
+ {"sr_YU" , C_ISO_8859_2 , C_ISO_8859_2},
+
+ {"mt_MT" , C_ISO_8859_3 , C_ISO_8859_3},
+
+ {"lt_LT.iso88594" , C_ISO_8859_4 , C_ISO_8859_4},
+ {"lt_LT.ISO8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
+ {"lt_LT.ISO_8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
+ {"lt_LT" , C_ISO_8859_13 , C_ISO_8859_13},
+
+ {"mk_MK" , C_ISO_8859_5 , C_ISO_8859_5},
+
+ {"ar_AE" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_BH" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_DZ" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_EG" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_IQ" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_JO" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_KW" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_LB" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_LY" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_MA" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_OM" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_QA" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_SA" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_SD" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_SY" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_TN" , C_ISO_8859_6 , C_ISO_8859_6},
+ {"ar_YE" , C_ISO_8859_6 , C_ISO_8859_6},
+
{"el_GR" , C_ISO_8859_7 , C_ISO_8859_7},
+ {"he_IL" , C_ISO_8859_8 , C_ISO_8859_8},
{"iw_IL" , C_ISO_8859_8 , C_ISO_8859_8},
{"tr_TR" , C_ISO_8859_9 , C_ISO_8859_9},
+ {"lv_LV" , C_ISO_8859_13 , C_ISO_8859_13},
+ {"mi_NZ" , C_ISO_8859_13 , C_ISO_8859_13},
+
+ {"cy_GB" , C_ISO_8859_14 , C_ISO_8859_14},
+
+ {"ar_IN" , C_UTF_8 , C_UTF_8},
+ {"en_IN" , C_UTF_8 , C_UTF_8},
+ {"se_NO" , C_UTF_8 , C_UTF_8},
+ {"ta_IN" , C_UTF_8 , C_UTF_8},
+ {"te_IN" , C_UTF_8 , C_UTF_8},
+ {"ur_PK" , C_UTF_8 , C_UTF_8},
+
{"th_TH" , C_TIS_620 , C_TIS_620},
/* {"th_TH" , C_WINDOWS_874}, */
/* {"th_TH" , C_ISO_8859_11}, */
- {"lt_LT.iso88594" , C_ISO_8859_4 , C_ISO_8859_4},
- {"lt_LT.ISO8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
- {"lt_LT.ISO_8859-4" , C_ISO_8859_4 , C_ISO_8859_4},
- {"lt_LT" , C_ISO_8859_13 , C_ISO_8859_13},
- {"lv_LV" , C_ISO_8859_13 , C_ISO_8859_13},
+ {"ka_GE" , C_GEORGIAN_PS , C_GEORGIAN_PS},
+ {"vi_VN.TCVN" , C_TCVN5712_1 , C_TCVN5712_1},
{"C" , C_US_ASCII , C_US_ASCII},
{"POSIX" , C_US_ASCII , C_US_ASCII},
return table;
}
-static gint str_case_equal(gconstpointer v, gconstpointer v2)
-{
- return strcasecmp((const gchar *)v, (const gchar *)v2) == 0;
-}
-
-static guint str_case_hash(gconstpointer key)
-{
- const gchar *p = key;
- guint h = *p;
-
- if (h) {
- h = tolower(h);
- for (p += 1; *p != '\0'; p++)
- h = (h << 5) - h + tolower(*p);
- }
-
- return h;
-}
-
static GHashTable *conv_get_charset_from_str_table(void)
{
static GHashTable *table;
return GPOINTER_TO_UINT(g_hash_table_lookup(table, charset));
}
-CharSet conv_get_current_charset(void)
+CharSet conv_get_locale_charset(void)
{
static CharSet cur_charset = -1;
const gchar *cur_locale;
/* "ja_JP.EUC" matches with "ja_JP.eucJP", "ja_JP.EUC" and
"ja_JP". "ja_JP" matches with "ja_JP.xxxx" and "ja" */
- if (!strncasecmp(cur_locale, locale_table[i].locale,
+ if (!g_ascii_strncasecmp(cur_locale, locale_table[i].locale,
strlen(locale_table[i].locale))) {
cur_charset = locale_table[i].charset;
return cur_charset;
} else if ((p = strchr(locale_table[i].locale, '_')) &&
!strchr(p + 1, '.')) {
if (strlen(cur_locale) == 2 &&
- !strncasecmp(cur_locale, locale_table[i].locale, 2)) {
+ !g_ascii_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
cur_charset = locale_table[i].charset;
return cur_charset;
}
return cur_charset;
}
-const gchar *conv_get_current_charset_str(void)
+const gchar *conv_get_locale_charset_str(void)
{
static const gchar *codeset = NULL;
if (!codeset)
- codeset = conv_get_charset_str(conv_get_current_charset());
+ codeset = conv_get_charset_str(conv_get_locale_charset());
+
+ return codeset ? codeset : CS_INTERNAL;
+}
+
+CharSet conv_get_internal_charset(void)
+{
+ return C_INTERNAL;
+}
- return codeset ? codeset : CS_US_ASCII;
+const gchar *conv_get_internal_charset_str(void)
+{
+ return CS_INTERNAL;
}
CharSet conv_get_outgoing_charset(void)
for (i = 0; i < sizeof(locale_table) / sizeof(locale_table[0]); i++) {
const gchar *p;
- if (!strncasecmp(cur_locale, locale_table[i].locale,
+ if (!g_ascii_strncasecmp(cur_locale, locale_table[i].locale,
strlen(locale_table[i].locale))) {
out_charset = locale_table[i].out_charset;
break;
} else if ((p = strchr(locale_table[i].locale, '_')) &&
!strchr(p + 1, '.')) {
if (strlen(cur_locale) == 2 &&
- !strncasecmp(cur_locale, locale_table[i].locale, 2)) {
+ !g_ascii_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
out_charset = locale_table[i].out_charset;
break;
}
}
}
-#if !HAVE_ICONV
- /* encoding conversion without iconv() is only supported
- on Japanese locale for now */
- if (out_charset == C_ISO_2022_JP)
- return out_charset;
- else
- return conv_get_current_charset();
-#endif
-
return out_charset;
}
const gchar *str;
if (prefs_common.outgoing_charset) {
- if (!isalpha(prefs_common.outgoing_charset[0])) {
+ if (!isalpha((guchar)prefs_common.outgoing_charset[0])) {
g_free(prefs_common.outgoing_charset);
prefs_common.outgoing_charset = g_strdup(CS_AUTO);
} else if (strcmp(prefs_common.outgoing_charset, CS_AUTO) != 0)
out_charset = conv_get_outgoing_charset();
str = conv_get_charset_str(out_charset);
- return str ? str : CS_US_ASCII;
+ return str ? str : CS_UTF_8;
+}
+
+gboolean conv_is_multibyte_encoding(CharSet encoding)
+{
+ switch (encoding) {
+ case C_EUC_JP:
+ case C_EUC_JP_MS:
+ case C_EUC_KR:
+ case C_EUC_TW:
+ case C_EUC_CN:
+ case C_ISO_2022_JP:
+ case C_ISO_2022_JP_2:
+ case C_ISO_2022_JP_3:
+ case C_ISO_2022_KR:
+ case C_ISO_2022_CN:
+ case C_SHIFT_JIS:
+ case C_GB2312:
+ case C_BIG5:
+ case C_UTF_8:
+ case C_UTF_7:
+ return TRUE;
+ default:
+ return FALSE;
+ }
}
const gchar *conv_get_current_locale(void)
{
- gchar *cur_locale;
+ const gchar *cur_locale;
cur_locale = g_getenv("LC_ALL");
if (!cur_locale) cur_locale = g_getenv("LC_CTYPE");
gint buflen;
CharSet cur_charset;
- cur_charset = conv_get_current_charset();
+ cur_charset = conv_get_locale_charset();
if (cur_charset == C_EUC_JP) {
buflen = strlen(str) * 2 + 1;
{
CharSet cur_charset;
- cur_charset = conv_get_current_charset();
+ cur_charset = conv_get_locale_charset();
if (cur_charset == C_EUC_JP) {
gchar *buf;
Xalloca(buf, buflen, return);
conv_anytodisp(buf, buflen, str);
unmime_header(outbuf, buf);
- } else
+ } else {
+ gchar *tmp = NULL;
unmime_header(outbuf, str);
+
+ if (outbuf && !g_utf8_validate(outbuf, -1, NULL)) {
+ if (conv_get_locale_charset() != C_INTERNAL)
+ tmp = conv_codeset_strdup(outbuf,
+ conv_get_locale_charset_str(),
+ CS_INTERNAL);
+
+ if (tmp) {
+ strncpy(outbuf, tmp, outlen-1);
+ g_free(tmp);
+ } else {
+ conv_unreadable_8bit(outbuf);
+ }
+ }
+ }
+
}
#define MAX_LINELEN 76
#define MIMESEP_BEGIN "=?"
#define MIMESEP_END "?="
-#define B64LEN(len) ((len) / 3 * 4 + ((len) % 3 ? 4 : 0))
-
#define LBREAK_IF_REQUIRED(cond, is_plain_text) \
{ \
- if (len - (destp - dest) < MAX_LINELEN + 2) { \
+ if (len - (destp - (guchar *)dest) < MAX_LINELEN + 2) { \
*destp = '\0'; \
return; \
} \
\
if ((cond) && *srcp) { \
- if (destp > dest && left < MAX_LINELEN - 1) { \
+ if (destp > (guchar *)dest && left < MAX_LINELEN - 1) { \
if (isspace(*(destp - 1))) \
destp--; \
else if (is_plain_text && isspace(*srcp)) \
}
void conv_encode_header(gchar *dest, gint len, const gchar *src,
- gint header_len)
+ gint header_len, gboolean addr_field)
{
const gchar *cur_encoding;
const gchar *out_encoding;
gint mimestr_len;
gchar *mimesep_enc;
gint left;
- const gchar *srcp = src;
- gchar *destp = dest;
+ const guchar *srcp = src;
+ guchar *destp = dest;
gboolean use_base64;
+ g_return_if_fail(g_utf8_validate(src, -1, NULL) == TRUE);
+
if (MB_CUR_MAX > 1) {
use_base64 = TRUE;
mimesep_enc = "?B?";
mimesep_enc = "?Q?";
}
- cur_encoding = conv_get_current_charset_str();
- if (!strcmp(cur_encoding, CS_US_ASCII))
- cur_encoding = CS_ISO_8859_1;
+ cur_encoding = CS_INTERNAL;
out_encoding = conv_get_outgoing_charset_str();
if (!strcmp(out_encoding, CS_US_ASCII))
out_encoding = CS_ISO_8859_1;
continue;
}
+ /* don't include parentheses in encoded strings */
+ if (addr_field && (*srcp == '(' || *srcp == ')')) {
+ LBREAK_IF_REQUIRED(left < 2, FALSE);
+ *destp++ = *srcp++;
+ left--;
+ }
+
while (1) {
gint mb_len = 0;
gint cur_len = 0;
gchar *part_str;
gchar *out_str;
gchar *enc_str;
- const gchar *p = srcp;
+ const guchar *p = srcp;
gint out_str_len;
gint out_enc_str_len;
gint mime_block_len;
while (*p != '\0') {
if (isspace(*p) && !is_next_nonascii(p + 1))
break;
+ /* don't include parentheses in encoded
+ strings */
+ if (addr_field && (*p == '(' || *p == ')'))
+ break;
- if (MB_CUR_MAX > 1) {
- mb_len = mblen(p, MB_CUR_MAX);
- if (mb_len < 0) {
- g_warning("conv_encode_header(): invalid multibyte character encountered\n");
- mb_len = 1;
- }
- } else
- mb_len = 1;
+ mb_len = g_utf8_skip[*p];
Xstrndup_a(part_str, srcp, cur_len + mb_len, );
out_str = conv_codeset_strdup
projects / claws.git / blobdiff