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);
conv_euctojis(outbuf, outlen, eucstr);
}
-static gchar valid_eucjp_tbl[][96] = {
- /* 0xa2a0 - 0xa2ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,
- 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,
- 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
- 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0 },
-
- /* 0xa3a0 - 0xa3ff */
- { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
- 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
- 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 },
-
- /* 0xa4a0 - 0xa4ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
-
- /* 0xa5a0 - 0xa5ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
-
- /* 0xa6a0 - 0xa6ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0,
- 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
-
- /* 0xa7a0 - 0xa7ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
-
- /* 0xa8a0 - 0xa8ff */
- { 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
- 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-};
-
-static gboolean isprintableeuckanji(guchar c1, guchar c2)
-{
- if (c1 <= 0xa0 || c1 >= 0xf5)
- return FALSE;
- if (c2 <= 0xa0 || c2 == 0xff)
- return FALSE;
-
- if (c1 >= 0xa9 && c1 <= 0xaf)
- return FALSE;
-
- if (c1 >= 0xa2 && c1 <= 0xa8)
- return (gboolean)valid_eucjp_tbl[c1 - 0xa2][c2 - 0xa0];
-
- if (c1 == 0xcf) {
- if (c2 >= 0xd4 && c2 <= 0xfe)
- return FALSE;
- } else if (c1 == 0xf4) {
- if (c2 >= 0xa7 && c2 <= 0xfe)
- return FALSE;
- }
-
- return TRUE;
-}
-
-static void conv_unreadable_eucjp(gchar *str)
-{
- register guchar *p = str;
-
- while (*p != '\0') {
- if (IS_ASCII(*p)) {
- /* convert CR+LF -> LF */
- if (*p == '\r' && *(p + 1) == '\n')
- memmove(p, p + 1, strlen(p));
- /* printable 7 bit code */
- p++;
- } else if (iseuckanji(*p)) {
- if (isprintableeuckanji(*p, *(p + 1))) {
- /* printable euc-jp code */
- p += 2;
- } else {
- /* substitute unprintable code */
- *p++ = SUBST_CHAR;
- if (*p != '\0') {
- if (IS_ASCII(*p))
- p++;
- else
- *p++ = SUBST_CHAR;
- }
- }
- } else if (iseuchwkana1(*p)) {
- if (iseuchwkana2(*(p + 1)))
- /* euc-jp hankaku kana */
- p += 2;
- else
- *p++ = SUBST_CHAR;
- } else if (iseucaux(*p)) {
- if (iseuckanji(*(p + 1)) && iseuckanji(*(p + 2))) {
- /* auxiliary kanji */
- p += 3;
- } else
- *p++ = SUBST_CHAR;
- } else
- /* substitute unprintable 1 byte code */
- *p++ = SUBST_CHAR;
- }
-}
-
static void conv_unreadable_8bit(gchar *str)
{
register guchar *p = str;
}
}
-static void conv_unreadable_latin(gchar *str)
-{
- register guchar *p = str;
-
- while (*p != '\0') {
- /* convert CR+LF -> LF */
- if (*p == '\r' && *(p + 1) == '\n')
- memmove(p, p + 1, strlen(p));
- else if ((*p & 0xff) >= 0x7f && (*p & 0xff) <= 0x9f)
- *p = SUBST_CHAR;
- p++;
- }
-}
-
#define NCV '\0'
void conv_mb_alnum(gchar *str)
strncpy2(outbuf, inbuf, outlen);
}
+static const gchar *
+conv_get_fallback_for_private_encoding(const gchar *encoding)
+{
+ if (encoding && (encoding[0] == 'X' || encoding[0] == 'x') &&
+ encoding[1] == '-') {
+ if (!g_ascii_strcasecmp(encoding, CS_X_GBK))
+ return CS_GBK;
+ }
+
+ return encoding;
+}
+
CodeConverter *conv_code_converter_new(const gchar *src_charset)
{
CodeConverter *conv;
+ src_charset = conv_get_fallback_for_private_encoding(src_charset);
+
conv = g_new0(CodeConverter, 1);
conv->code_conv_func = conv_get_code_conv_func(src_charset, NULL);
conv->charset_str = g_strdup(src_charset);
size_t len;
CodeConvFunc conv_func;
+ src_code = conv_get_fallback_for_private_encoding(src_code);
conv_func = conv_get_code_conv_func(src_code, dest_code);
if (conv_func != conv_noconv) {
len = (strlen(inbuf) + 1) * 3;
/* auto detection mode */
if (!src_charset_str && !dest_charset_str) {
- if (src_charset == C_EUC_JP || src_charset == C_SHIFT_JIS)
+ if (conv_is_ja_locale())
return conv_anytodisp;
else
return conv_noconv;
{"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.GBK" , C_GBK , C_GBK},
{"zh_CN" , C_GB2312 , C_GB2312},
{"zh_HK" , C_BIG5_HKSCS , C_BIG5_HKSCS},
{"zh_TW.eucTW" , C_EUC_TW , C_BIG5},
CharSet out_charset;
const gchar *str;
- if (prefs_common.outgoing_charset) {
- 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)
- return prefs_common.outgoing_charset;
- }
-
out_charset = conv_get_outgoing_charset();
str = conv_get_charset_str(out_charset);
case C_ISO_2022_CN:
case C_SHIFT_JIS:
case C_GB2312:
+ case C_GBK:
case C_BIG5:
case C_UTF_8:
case C_UTF_7:
return cur_locale;
}
+gboolean conv_is_ja_locale(void)
+{
+ static gint is_ja_locale = -1;
+ const gchar *cur_locale;
+
+ if (is_ja_locale != -1)
+ return is_ja_locale != 0;
+
+ is_ja_locale = 0;
+ cur_locale = conv_get_current_locale();
+ if (cur_locale) {
+ if (g_ascii_strncasecmp(cur_locale, "ja", 2) == 0)
+ is_ja_locale = 1;
+ }
+
+ return is_ja_locale != 0;
+}
+
gchar *conv_unmime_header(const gchar *str, const gchar *default_encoding)
{
gchar buf[BUFFSIZE];
}
}
- if (conv_get_locale_charset() == C_EUC_JP)
+ if (conv_is_ja_locale())
conv_anytodisp(buf, sizeof(buf), str);
else
conv_localetodisp(buf, sizeof(buf), str);