/*
* Sylpheed -- a GTK+ based, lightweight, and fast e-mail client
- * Copyright (C) 1999-2007 Hiroyuki Yamamoto and the Claws Mail team
+ * Copyright (C) 1999-2012 Hiroyuki Yamamoto and the Claws Mail team
*
* 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
#ifdef HAVE_CONFIG_H
# include "config.h"
+#include "claws-features.h"
#endif
#include "defs.h"
#include "codeconv.h"
#include "unmime.h"
-#include "base64.h"
#include "quoted-printable.h"
#include "utils.h"
#include "prefs_common.h"
static CharSet conv_guess_ja_encoding(const gchar *str);
static gboolean conv_is_ja_locale (void);
-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 gint conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint 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 gint conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint 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 gint conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf);
static void conv_unreadable_8bit(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 gint conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint 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 gint conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf);
+static gint conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf);
static gboolean strict_mode = FALSE;
strict_mode = mode;
}
-static void conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_jistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
- guchar *out = outbuf;
+ gchar *out = outbuf;
JISState state = JIS_ASCII;
- while (*in != '\0') {
+ /*
+ * Loop outputs up to 3 bytes in each pass (aux kanji) and we
+ * need 1 byte to terminate the output
+ */
+ while (*in != '\0' && (out - outbuf) < outlen - 4) {
if (*in == ESC) {
in++;
if (*in == '$') {
}
*out = '\0';
+ return 0;
}
#define JIS_HWDAKUTEN 0x5e
return 1;
}
-static void conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_euctojis(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
- guchar *out = outbuf;
+ gchar *out = outbuf;
JISState state = JIS_ASCII;
- while (*in != '\0') {
+ /*
+ * Loop outputs up to 6 bytes in each pass (aux shift + aux
+ * kanji) and we need up to 4 bytes to terminate the output
+ * (ASCII shift + null)
+ */
+ while (*in != '\0' && (out - outbuf) < outlen - 10) {
if (IS_ASCII(*in)) {
K_OUT();
*out++ = *in++;
K_OUT();
*out = '\0';
+ return 0;
}
-static void conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_sjistoeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
const guchar *in = inbuf;
- guchar *out = outbuf;
+ gchar *out = outbuf;
- while (*in != '\0') {
+ /*
+ * Loop outputs up to 2 bytes in each pass and we need 1 byte
+ * to terminate the output
+ */
+ while (*in != '\0' && (out - outbuf) < outlen - 3) {
if (IS_ASCII(*in)) {
*out++ = *in++;
} else if (issjiskanji1(*in)) {
}
*out = '\0';
+ return 0;
}
-static void conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_jistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
{
gchar *eucstr;
- Xalloca(eucstr, outlen, return);
+ Xalloca(eucstr, outlen, return -1);
- conv_jistoeuc(eucstr, outlen, inbuf);
- conv_euctoutf8(outbuf, outlen, eucstr);
+ if (conv_jistoeuc(eucstr, outlen, inbuf) <0)
+ return -1;
+ if (conv_euctoutf8(outbuf, outlen, eucstr) < 0)
+ return -1;
+ return 0;
}
-static void conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_sjistoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
{
gchar *tmpstr;
if (tmpstr) {
strncpy2(outbuf, tmpstr, outlen);
g_free(tmpstr);
- } else
+ return 0;
+ } else {
strncpy2(outbuf, inbuf, outlen);
+ return -1;
+ }
}
-static void conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_euctoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
{
static iconv_t cd = (iconv_t)-1;
static gboolean iconv_ok = TRUE;
if (cd == (iconv_t)-1) {
if (!iconv_ok) {
strncpy2(outbuf, inbuf, outlen);
- return;
+ return -1;
}
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_warning("conv_euctoutf8(): %s",
g_strerror(errno));
iconv_ok = FALSE;
strncpy2(outbuf, inbuf, outlen);
- return;
+ return -1;
}
}
}
if (tmpstr) {
strncpy2(outbuf, tmpstr, outlen);
g_free(tmpstr);
- } else
+ return 0;
+ } else {
strncpy2(outbuf, inbuf, outlen);
+ return -1;
+ }
}
-static void conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_anytoutf8(gchar *outbuf, gint outlen, const gchar *inbuf)
{
+ gint r = -1;
switch (conv_guess_ja_encoding(inbuf)) {
case C_ISO_2022_JP:
- conv_jistoutf8(outbuf, outlen, inbuf);
+ r = conv_jistoutf8(outbuf, outlen, inbuf);
break;
case C_SHIFT_JIS:
- conv_sjistoutf8(outbuf, outlen, inbuf);
+ r = conv_sjistoutf8(outbuf, outlen, inbuf);
break;
case C_EUC_JP:
- conv_euctoutf8(outbuf, outlen, inbuf);
+ r = conv_euctoutf8(outbuf, outlen, inbuf);
break;
default:
+ r = 0;
strncpy2(outbuf, inbuf, outlen);
break;
}
+
+ return r;
}
-static void conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_utf8toeuc(gchar *outbuf, gint outlen, const gchar *inbuf)
{
static iconv_t cd = (iconv_t)-1;
static gboolean iconv_ok = TRUE;
if (cd == (iconv_t)-1) {
if (!iconv_ok) {
strncpy2(outbuf, inbuf, outlen);
- return;
+ return -1;
}
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_warning("conv_utf8toeuc(): %s",
g_strerror(errno));
iconv_ok = FALSE;
strncpy2(outbuf, inbuf, outlen);
- return;
+ return -1;
}
}
}
if (tmpstr) {
strncpy2(outbuf, tmpstr, outlen);
g_free(tmpstr);
- } else
+ return 0;
+ } else {
strncpy2(outbuf, inbuf, outlen);
+ return -1;
+ }
}
-static void conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_utf8tojis(gchar *outbuf, gint outlen, const gchar *inbuf)
{
gchar *eucstr;
- Xalloca(eucstr, outlen, return);
+ Xalloca(eucstr, outlen, return -1);
- conv_utf8toeuc(eucstr, outlen, inbuf);
- conv_euctojis(outbuf, outlen, eucstr);
+ if (conv_utf8toeuc(eucstr, outlen, inbuf) < 0)
+ return -1;
+ if (conv_euctojis(outbuf, outlen, eucstr) < 0)
+ return -1;
+
+ return 0;
}
static void conv_unreadable_8bit(gchar *str)
return guessed;
}
-static void conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_jistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_jistoutf8(outbuf, outlen, inbuf);
+ return conv_jistoutf8(outbuf, outlen, inbuf);
}
-static void conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_sjistodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_sjistoutf8(outbuf, outlen, inbuf);
+ return conv_sjistoutf8(outbuf, outlen, inbuf);
}
-static void conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_euctodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_euctoutf8(outbuf, outlen, inbuf);
+ return conv_euctoutf8(outbuf, outlen, inbuf);
}
void conv_utf8todisp(gchar *outbuf, gint outlen, const gchar *inbuf)
conv_ustodisp(outbuf, outlen, inbuf);
}
-static void conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_anytodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
- conv_anytoutf8(outbuf, outlen, inbuf);
+ gint r = 0;
+ if (conv_anytoutf8(outbuf, outlen, inbuf) < 0)
+ r = -1;
if (g_utf8_validate(outbuf, -1, NULL) != TRUE)
conv_unreadable_8bit(outbuf);
+ return r;
}
-static void conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_ustodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
{
strncpy2(outbuf, inbuf, outlen);
conv_unreadable_8bit(outbuf);
+
+ return 0;
}
void conv_localetodisp(gchar *outbuf, gint outlen, const gchar *inbuf)
}
}
-static void conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf)
+static gint conv_noconv(gchar *outbuf, gint outlen, const gchar *inbuf)
{
strncpy2(outbuf, inbuf, outlen);
+ return 0;
}
static const gchar *
{
if (encoding && (encoding[0] == 'X' || encoding[0] == 'x') &&
encoding[1] == '-') {
+ if (!g_ascii_strcasecmp(encoding, CS_X_MACCYR))
+ return CS_MACCYR;
if (!g_ascii_strcasecmp(encoding, CS_X_GBK))
return CS_GBK;
}
const gchar *inbuf)
{
if (conv->code_conv_func != conv_noconv)
- conv->code_conv_func(outbuf, outlen, inbuf);
+ return conv->code_conv_func(outbuf, outlen, inbuf);
else {
gchar *str;
size_t len;
CodeConvFunc conv_func;
- if (!strcmp2(src_code, dest_code))
+ if (!strcmp2(src_code, dest_code)) {
+ CharSet dest_charset = conv_get_charset_from_str(dest_code);
+ if (strict_mode && dest_charset == C_UTF_8) {
+ /* ensure valid UTF-8 if target is UTF-8 */
+ if (!g_utf8_validate(inbuf, -1, NULL)) {
+ return NULL;
+ }
+ }
+ /* otherwise, try for a lucky day */
return g_strdup(inbuf);
+ }
src_code = conv_get_fallback_for_private_encoding(src_code);
conv_func = conv_get_code_conv_func(src_code, dest_code);
buf = g_malloc(len);
if (!buf) return NULL;
- conv_func(buf, len, inbuf);
- return g_realloc(buf, strlen(buf) + 1);
+ if (conv_func(buf, len, inbuf) == 0 || !strict_mode)
+ return g_realloc(buf, strlen(buf) + 1);
+ else {
+ g_free(buf);
+ return NULL;
+ }
}
return conv_iconv_strdup(inbuf, src_code, dest_code);
} else if (E2BIG == errno) {
EXPAND_BUF();
} else {
- g_warning("conv_iconv_strdup(): %s\n",
+ g_warning("conv_iconv_strdup(): %s",
g_strerror(errno));
break;
}
if (E2BIG == errno) {
EXPAND_BUF();
} else {
- g_warning("conv_iconv_strdup(): %s\n",
+ g_warning("conv_iconv_strdup(): %s",
g_strerror(errno));
break;
}
{C_WINDOWS_1257, CS_WINDOWS_1257},
{C_WINDOWS_1258, CS_WINDOWS_1258},
{C_KOI8_R, CS_KOI8_R},
+ {C_MACCYR, CS_MACCYR},
{C_KOI8_T, CS_KOI8_T},
{C_KOI8_U, CS_KOI8_U},
{C_ISO_2022_JP, CS_ISO_2022_JP},
{C_EUC_KR, CS_EUC_KR},
{C_ISO_2022_CN, CS_ISO_2022_CN},
{C_EUC_CN, CS_EUC_CN},
+ {C_GB18030, CS_GB18030},
{C_GB2312, CS_GB2312},
{C_GBK, CS_GBK},
{C_EUC_TW, CS_EUC_TW},
#endif
{"ko_KR.EUC-KR" , C_EUC_KR , C_EUC_KR},
{"ko_KR" , C_EUC_KR , C_EUC_KR},
+ {"zh_CN.GB18030" , C_GB18030 , C_GB18030},
{"zh_CN.GB2312" , C_GB2312 , C_GB2312},
{"zh_CN.GBK" , C_GBK , C_GBK},
- {"zh_CN" , C_GB2312 , C_GB2312},
+ {"zh_CN" , C_GB18030 , C_GB18030},
{"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},
{"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},
+#ifdef G_OS_WIN32
+ {"ru_RU" , C_WINDOWS_1251, C_KOI8_R},
+#else
{"ru_RU" , C_ISO_8859_5 , C_KOI8_R},
+#endif
{"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},
return cur_charset;
}
- if (strcasestr(cur_locale, ".UTF-8") ||
- strcasestr(cur_locale, ".utf8")) {
+ if (strcasestr(cur_locale, "UTF-8") ||
+ strcasestr(cur_locale, "utf8")) {
cur_charset = C_UTF_8;
return cur_charset;
}
static CharSet cur_charset = -1;
const gchar *cur_locale;
const gchar *p;
- gchar *tmp;
gint i;
- if (prefs_common.broken_are_utf8)
- return conv_get_locale_charset();
-
- if (cur_charset != -1)
+ if (prefs_common.broken_are_utf8) {
+ cur_charset = C_UTF_8;
return cur_charset;
+ }
cur_locale = conv_get_current_locale();
if (!cur_locale) {
return cur_charset;
}
- if (strcasestr(cur_locale, "UTF-8")) {
- tmp = g_strdup(cur_locale);
- *(strcasestr(tmp, ".UTF-8")) = '\0';
- cur_locale = tmp;
+ if (strcasestr(cur_locale, "UTF-8") ||
+ strcasestr(cur_locale, "utf8")) {
+ cur_charset = C_UTF_8;
+ return cur_charset;
}
if ((p = strcasestr(cur_locale, "@euro")) && p[5] == '\0') {
return out_charset;
}
- if (strcasestr(cur_locale, "UTF-8")) {
+ if (strcasestr(cur_locale, "UTF-8") ||
+ strcasestr(cur_locale, "utf8")) {
out_charset = C_UTF_8;
return out_charset;
}
return is_ja_locale != 0;
}
-gchar *conv_unmime_header(const gchar *str, const gchar *default_encoding)
+gchar *conv_unmime_header(const gchar *str, const gchar *default_encoding,
+ gboolean addr_field)
{
gchar buf[BUFFSIZE];
if (is_ascii_str(str))
- return unmime_header(str);
+ return unmime_header(str, addr_field);
if (default_encoding) {
gchar *utf8_buf;
if (utf8_buf) {
gchar *decoded_str;
- decoded_str = unmime_header(utf8_buf);
+ decoded_str = unmime_header(utf8_buf, addr_field);
g_free(utf8_buf);
return decoded_str;
}
else
conv_localetodisp(buf, sizeof(buf), str);
- return unmime_header(buf);
+ return unmime_header(buf, addr_field);
}
#define MAX_LINELEN 76
*destp++ = ' '; \
left = MAX_LINELEN - 1; \
} \
+ } else if (destp == (guchar *)dest && left < 7) { \
+ if (is_plain_text && isspace(*srcp)) \
+ srcp++; \
+ if (*srcp) { \
+ *destp++ = '\n'; \
+ *destp++ = ' '; \
+ left = MAX_LINELEN - 1; \
+ } \
} \
} \
}
+#define B64LEN(len) ((len) / 3 * 4 + ((len) % 3 ? 4 : 0))
+
void conv_encode_header_full(gchar *dest, gint len, const gchar *src,
gint header_len, gboolean addr_field,
const gchar *out_encoding_)
guchar *destp = dest;
gboolean use_base64;
- g_return_if_fail(g_utf8_validate(src, -1, NULL) == TRUE);
+ cm_return_if_fail(g_utf8_validate(src, -1, NULL) == TRUE);
+ cm_return_if_fail(destp != NULL);
if (MB_CUR_MAX > 1) {
use_base64 = TRUE;
*dest = '\0';
return;
} else {
- g_warning("conv_encode_header(): code conversion failed\n");
+ g_warning("conv_encode_header(): code conversion failed");
conv_unreadable_8bit(part_str);
out_str = g_strdup(part_str);
}
cur_len += mb_len;
p += mb_len;
} else if (cur_len == 0) {
+ left = 0;
LBREAK_IF_REQUIRED(1, FALSE);
continue;
} else {
out_str = conv_codeset_strdup
(part_str, cur_encoding, out_encoding);
if (!out_str) {
- g_warning("conv_encode_header(): code conversion failed\n");
+ g_warning("conv_encode_header(): code conversion failed");
conv_unreadable_8bit(part_str);
out_str = g_strdup(part_str);
}
out_enc_str_len =
qp_get_q_encoding_len(out_str);
- Xalloca(enc_str, out_enc_str_len + 1, );
if (use_base64)
- base64_encode(enc_str, out_str, out_str_len);
- else
+ enc_str = g_base64_encode(out_str, out_str_len);
+ else {
+ Xalloca(enc_str, out_enc_str_len + 1, );
qp_q_encode(enc_str, out_str);
+ }
g_free(out_str);
g_snprintf(destp, mime_block_len + 1,
MIMESEP_BEGIN "%s%s%s" MIMESEP_END,
out_encoding, mimesep_enc, enc_str);
+
+ if (use_base64)
+ g_free(enc_str);
+
destp += mime_block_len;
srcp += cur_len;
}
#undef LBREAK_IF_REQUIRED
+#undef B64LEN
+
gchar *conv_filename_from_utf8(const gchar *utf8_file)
{
gchar *fs_file;
utf8_file = g_filename_to_utf8(fs_file, -1, NULL, NULL, &error);
if (error) {
- g_warning("failed to convert encoding of file name: %s\n",
+ g_warning("failed to convert encoding of file name: %s",
error->message);
g_error_free(error);
}
projects / claws.git / blobdiff