2005-03-04 [paul] 1.0.1cvs21
[claws.git] / src / codeconv.c
index 15c3a5f3b3f1e9ee529025a7e372ef36112b62e2..d177f743c3d65aae811451ff1d7b8607a658b808 100644 (file)
@@ -1,6 +1,6 @@
 /*
  * 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
@@ -173,6 +173,72 @@ void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
        *out = '\0';
 }
 
+#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;
+}
+
 void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
 {
        const guchar *in = inbuf;
@@ -180,7 +246,7 @@ void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
        JISState state = JIS_ASCII;
 
        while (*in != '\0') {
-               if (isascii(*in)) {
+               if (IS_ASCII(*in)) {
                        K_OUT();
                        *out++ = *in++;
                } else if (iseuckanji(*in)) {
@@ -192,19 +258,43 @@ void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
                                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++;
                                }
@@ -217,10 +307,10 @@ void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
                                *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++;
                                        }
@@ -243,7 +333,7 @@ void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
        guchar *out = outbuf;
 
        while (*in != '\0') {
-               if (isascii(*in)) {
+               if (IS_ASCII(*in)) {
                        *out++ = *in++;
                } else if (issjiskanji1(*in)) {
                        if (issjiskanji2(*(in + 1))) {
@@ -266,7 +356,7 @@ void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
                        } else {
                                *out++ = SUBST_CHAR;
                                in++;
-                               if (*in != '\0' && !isascii(*in)) {
+                               if (*in != '\0' && !IS_ASCII(*in)) {
                                        *out++ = SUBST_CHAR;
                                        in++;
                                }
@@ -382,10 +472,10 @@ static gboolean isprintableeuckanji(guchar c1, guchar c2)
                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;
        }
 
@@ -397,7 +487,7 @@ 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));
@@ -411,7 +501,7 @@ void conv_unreadable_eucjp(gchar *str)
                                /* substitute unprintable code */
                                *p++ = SUBST_CHAR;
                                if (*p != '\0') {
-                                       if (isascii(*p))
+                                       if (IS_ASCII(*p))
                                                p++;
                                        else
                                                *p++ = SUBST_CHAR;
@@ -443,7 +533,7 @@ void conv_unreadable_8bit(gchar *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++;
        }
 }
@@ -462,6 +552,34 @@ void conv_unreadable_latin(gchar *str)
        }
 }
 
+void conv_unreadable_locale(gchar *str)
+{
+       switch (conv_get_current_charset()) {
+       case C_US_ASCII:
+       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:
+               conv_unreadable_latin(str);
+               break;
+       case C_EUC_JP:
+               conv_unreadable_eucjp(str);
+               break;
+       default:
+               break;
+       }
+}
+
 #define NCV    '\0'
 
 void conv_mb_alnum(gchar *str)
@@ -538,7 +656,7 @@ CharSet conv_guess_ja_encoding(const gchar *str)
                        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)
@@ -606,35 +724,15 @@ void conv_latintodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
        conv_unreadable_latin(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);
+       conv_unreadable_locale(outbuf);
 }
 
-void conv_localetodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+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)
@@ -735,7 +833,9 @@ CodeConvFunc conv_get_code_conv_func(const gchar *src_charset_str,
        switch (src_charset) {
        case C_ISO_2022_JP:
        case C_ISO_2022_JP_2:
-               if (dest_charset == C_AUTO)
+       case C_ISO_2022_JP_3:
+               if (dest_charset == C_AUTO &&
+                   conv_get_current_charset() == C_EUC_JP)
                        code_conv = conv_jistodisp;
                else if (dest_charset == C_EUC_JP)
                        code_conv = conv_jistoeuc;
@@ -746,28 +846,37 @@ CodeConvFunc conv_get_code_conv_func(const gchar *src_charset_str,
                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:
-               if (dest_charset == C_AUTO)
+               if (dest_charset == C_AUTO &&
+                   (conv_get_current_charset() == src_charset ||
+                    MB_CUR_MAX > 1))
                        code_conv = conv_latintodisp;
                break;
        case C_SHIFT_JIS:
-               if (dest_charset == C_AUTO)
+               if (dest_charset == C_AUTO &&
+                   conv_get_current_charset() == C_EUC_JP)
                        code_conv = conv_sjistodisp;
                else if (dest_charset == C_EUC_JP)
                        code_conv = conv_sjistoeuc;
                break;
        case C_EUC_JP:
-               if (dest_charset == C_AUTO)
+               if (dest_charset == C_AUTO &&
+                   conv_get_current_charset() == C_EUC_JP)
                        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;
                break;
        default:
@@ -785,11 +894,12 @@ gchar *conv_iconv_strdup(const gchar *inbuf,
        const gchar *inbuf_p;
        gchar *outbuf;
        gchar *outbuf_p;
-       gint in_size;
-       gint in_left;
-       gint out_size;
-       gint out_left;
-       gint n_conv;
+       size_t in_size;
+       size_t in_left;
+       size_t out_size;
+       size_t out_left;
+       size_t n_conv;
+       size_t len;
 
        if (!src_code)
                src_code = conv_get_outgoing_charset_str();
@@ -797,11 +907,11 @@ gchar *conv_iconv_strdup(const gchar *inbuf,
                dest_code = conv_get_current_charset_str();
 
        /* don't convert if current codeset is US-ASCII */
-       if (!strcasecmp(dest_code, CS_US_ASCII))
+       if (!g_strcasecmp(dest_code, CS_US_ASCII))
                return g_strdup(inbuf);
 
        /* don't convert if src and dest codeset are identical */
-       if (!strcasecmp(src_code, dest_code))
+       if (!g_strcasecmp(src_code, dest_code))
                return g_strdup(inbuf);
 
        cd = iconv_open(dest_code, src_code);
@@ -809,40 +919,59 @@ gchar *conv_iconv_strdup(const gchar *inbuf,
                return NULL;
 
        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) {
                        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
+
+       len = outbuf_p - outbuf;
+       outbuf = g_realloc(outbuf, len + 1);
+       outbuf[len] = '\0';
 
        iconv_close(cd);
 
@@ -857,23 +986,46 @@ static const struct {
        {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_SHIFT_JIS,           CS_SHIFT_JIS},
@@ -884,10 +1036,14 @@ static const struct {
        {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 {
@@ -896,61 +1052,174 @@ 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},
@@ -979,25 +1248,6 @@ static GHashTable *conv_get_charset_to_str_table(void)
        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;
@@ -1065,14 +1315,14 @@ CharSet conv_get_current_charset(void)
 
                /* "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_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_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
                                cur_charset = locale_table[i].charset;
                                return cur_charset;
                        }
@@ -1117,14 +1367,14 @@ 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_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_strncasecmp(cur_locale, locale_table[i].locale, 2)) {
                                out_charset = locale_table[i].out_charset;
                                break;
                        }
@@ -1149,7 +1399,7 @@ const gchar *conv_get_outgoing_charset_str(void)
        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)
@@ -1162,14 +1412,40 @@ const gchar *conv_get_outgoing_charset_str(void)
        return str ? str : CS_US_ASCII;
 }
 
+gboolean conv_is_multibyte_encoding(CharSet encoding)
+{
+       switch (encoding) {
+       case C_EUC_JP:
+       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;
 
        cur_locale = g_getenv("LC_ALL");
-       if (!cur_locale) cur_locale = g_getenv("LC_CTYPE");
-       if (!cur_locale) cur_locale = g_getenv("LANG");
-       if (!cur_locale) cur_locale = setlocale(LC_CTYPE, NULL);
+       if (!cur_locale || !strlen(cur_locale)) 
+               cur_locale = g_getenv("LC_CTYPE");
+       if (!cur_locale || !strlen(cur_locale)) 
+               cur_locale = g_getenv("LANG");
+       if (!cur_locale || !strlen(cur_locale)) 
+               cur_locale = setlocale(LC_CTYPE, NULL);
 
        debug_print("current locale: %s\n",
                    cur_locale ? cur_locale : "(none)");
@@ -1177,27 +1453,6 @@ const gchar *conv_get_current_locale(void)
        return cur_locale;
 }
 
-void conv_unmime_header_overwrite(gchar *str)
-{
-       gchar *buf;
-       gint buflen;
-       CharSet cur_charset;
-
-       cur_charset = conv_get_current_charset();
-
-       if (cur_charset == C_EUC_JP) {
-               buflen = strlen(str) * 2 + 1;
-               Xalloca(buf, buflen, return);
-               conv_anytodisp(buf, buflen, str);
-               unmime_header(str, buf);
-       } else {
-               buflen = strlen(str) + 1;
-               Xalloca(buf, buflen, return);
-               unmime_header(buf, str);
-               strncpy2(str, buf, buflen);
-       }
-}
-
 void conv_unmime_header(gchar *outbuf, gint outlen, const gchar *str,
                        const gchar *charset)
 {
@@ -1222,17 +1477,15 @@ void conv_unmime_header(gchar *outbuf, gint outlen, const gchar *str,
 #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))       \
@@ -1247,15 +1500,15 @@ void conv_unmime_header(gchar *outbuf, gint outlen, const gchar *str,
 }
 
 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;
 
        if (MB_CUR_MAX > 1) {
@@ -1303,13 +1556,20 @@ void conv_encode_header(gchar *dest, gint len, const gchar *src,
                        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;
@@ -1318,6 +1578,10 @@ void conv_encode_header(gchar *dest, gint len, const gchar *src,
                        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);